]>
Commit | Line | Data |
---|---|---|
4fa74b52 RG |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | # Author: Ricardo Garcia Gonzalez | |
64a6f26c | 4 | # Author: Danny Colligan |
49c0028a | 5 | # Author: Benjamin Johnson |
4fa74b52 | 6 | # License: Public domain code |
80066952 | 7 | import cookielib |
4fa74b52 RG |
8 | import htmlentitydefs |
9 | import httplib | |
2546e767 | 10 | import locale |
4fa74b52 RG |
11 | import math |
12 | import netrc | |
13 | import os | |
14 | import os.path | |
15 | import re | |
16 | import socket | |
17 | import string | |
0487b407 | 18 | import subprocess |
4fa74b52 RG |
19 | import sys |
20 | import time | |
21 | import urllib | |
22 | import urllib2 | |
a04e80a4 RG |
23 | |
24 | # parse_qs was moved from the cgi module to the urlparse module recently. | |
25 | try: | |
26 | from urlparse import parse_qs | |
27 | except ImportError: | |
28 | from cgi import parse_qs | |
4fa74b52 | 29 | |
f995f712 | 30 | std_headers = { |
a6a61601 | 31 | 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.11) Gecko/20101019 Firefox/3.6.11', |
4fa74b52 | 32 | 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', |
96942e62 | 33 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', |
4fa74b52 RG |
34 | 'Accept-Language': 'en-us,en;q=0.5', |
35 | } | |
36 | ||
37 | simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') | |
38 | ||
eae2666c RG |
39 | def preferredencoding(): |
40 | """Get preferred encoding. | |
41 | ||
42 | Returns the best encoding scheme for the system, based on | |
43 | locale.getpreferredencoding() and some further tweaks. | |
44 | """ | |
f94b636c RG |
45 | def yield_preferredencoding(): |
46 | try: | |
47 | pref = locale.getpreferredencoding() | |
48 | u'TEST'.encode(pref) | |
49 | except: | |
50 | pref = 'UTF-8' | |
51 | while True: | |
52 | yield pref | |
53 | return yield_preferredencoding().next() | |
eae2666c | 54 | |
490fd7ae RG |
55 | def htmlentity_transform(matchobj): |
56 | """Transforms an HTML entity to a Unicode character. | |
57 | ||
58 | This function receives a match object and is intended to be used with | |
59 | the re.sub() function. | |
60 | """ | |
61 | entity = matchobj.group(1) | |
62 | ||
63 | # Known non-numeric HTML entity | |
64 | if entity in htmlentitydefs.name2codepoint: | |
65 | return unichr(htmlentitydefs.name2codepoint[entity]) | |
66 | ||
67 | # Unicode character | |
68 | mobj = re.match(ur'(?u)#(x?\d+)', entity) | |
69 | if mobj is not None: | |
70 | numstr = mobj.group(1) | |
71 | if numstr.startswith(u'x'): | |
72 | base = 16 | |
73 | numstr = u'0%s' % numstr | |
74 | else: | |
75 | base = 10 | |
76 | return unichr(long(numstr, base)) | |
77 | ||
78 | # Unknown entity in name, return its literal representation | |
79 | return (u'&%s;' % entity) | |
80 | ||
81 | def sanitize_title(utitle): | |
31bcb480 | 82 | """Sanitizes a video title so it could be used as part of a filename.""" |
490fd7ae | 83 | utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) |
490fd7ae RG |
84 | return utitle.replace(unicode(os.sep), u'%') |
85 | ||
31bcb480 RG |
86 | def sanitize_open(filename, open_mode): |
87 | """Try to open the given filename, and slightly tweak it if this fails. | |
88 | ||
89 | Attempts to open the given filename. If this fails, it tries to change | |
90 | the filename slightly, step by step, until it's either able to open it | |
91 | or it fails and raises a final exception, like the standard open() | |
92 | function. | |
93 | ||
94 | It returns the tuple (stream, definitive_file_name). | |
95 | """ | |
96 | try: | |
131bc765 | 97 | if filename == u'-': |
e08878f4 RG |
98 | if sys.platform == 'win32': |
99 | import msvcrt | |
100 | msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) | |
131bc765 | 101 | return (sys.stdout, filename) |
31bcb480 RG |
102 | stream = open(filename, open_mode) |
103 | return (stream, filename) | |
104 | except (IOError, OSError), err: | |
105 | # In case of error, try to remove win32 forbidden chars | |
ca6a11fa | 106 | filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename) |
31bcb480 RG |
107 | |
108 | # An exception here should be caught in the caller | |
109 | stream = open(filename, open_mode) | |
110 | return (stream, filename) | |
111 | ||
112 | ||
e5bf0f55 RG |
113 | class DownloadError(Exception): |
114 | """Download Error exception. | |
115 | ||
116 | This exception may be thrown by FileDownloader objects if they are not | |
117 | configured to continue on errors. They will contain the appropriate | |
118 | error message. | |
119 | """ | |
120 | pass | |
121 | ||
122 | class SameFileError(Exception): | |
123 | """Same File exception. | |
124 | ||
125 | This exception will be thrown by FileDownloader objects if they detect | |
126 | multiple files would have to be downloaded to the same file on disk. | |
127 | """ | |
128 | pass | |
129 | ||
65cd34c5 RG |
130 | class PostProcessingError(Exception): |
131 | """Post Processing exception. | |
132 | ||
133 | This exception may be raised by PostProcessor's .run() method to | |
134 | indicate an error in the postprocessing task. | |
135 | """ | |
136 | pass | |
137 | ||
73f4e7af | 138 | class UnavailableVideoError(Exception): |
7b7759f5 | 139 | """Unavailable Format exception. |
140 | ||
141 | This exception will be thrown when a video is requested | |
142 | in a format that is not available for that video. | |
143 | """ | |
d69a1c91 RG |
144 | pass |
145 | ||
146 | class ContentTooShortError(Exception): | |
147 | """Content Too Short exception. | |
148 | ||
149 | This exception may be raised by FileDownloader objects when a file they | |
150 | download is too small for what the server announced first, indicating | |
151 | the connection was probably interrupted. | |
152 | """ | |
153 | # Both in bytes | |
154 | downloaded = None | |
155 | expected = None | |
156 | ||
157 | def __init__(self, downloaded, expected): | |
158 | self.downloaded = downloaded | |
159 | self.expected = expected | |
7b7759f5 | 160 | |
4fa74b52 RG |
161 | class FileDownloader(object): |
162 | """File Downloader class. | |
163 | ||
164 | File downloader objects are the ones responsible of downloading the | |
165 | actual video file and writing it to disk if the user has requested | |
166 | it, among some other tasks. In most cases there should be one per | |
167 | program. As, given a video URL, the downloader doesn't know how to | |
168 | extract all the needed information, task that InfoExtractors do, it | |
169 | has to pass the URL to one of them. | |
170 | ||
171 | For this, file downloader objects have a method that allows | |
172 | InfoExtractors to be registered in a given order. When it is passed | |
173 | a URL, the file downloader handles it to the first InfoExtractor it | |
2851b2ca RG |
174 | finds that reports being able to handle it. The InfoExtractor extracts |
175 | all the information about the video or videos the URL refers to, and | |
176 | asks the FileDownloader to process the video information, possibly | |
177 | downloading the video. | |
4fa74b52 RG |
178 | |
179 | File downloaders accept a lot of parameters. In order not to saturate | |
180 | the object constructor with arguments, it receives a dictionary of | |
d0a9affb RG |
181 | options instead. These options are available through the params |
182 | attribute for the InfoExtractors to use. The FileDownloader also | |
183 | registers itself as the downloader in charge for the InfoExtractors | |
184 | that are added to it, so this is a "mutual registration". | |
4fa74b52 RG |
185 | |
186 | Available options: | |
187 | ||
80066952 RG |
188 | username: Username for authentication purposes. |
189 | password: Password for authentication purposes. | |
190 | usenetrc: Use netrc for authentication instead. | |
191 | quiet: Do not print messages to stdout. | |
192 | forceurl: Force printing final URL. | |
193 | forcetitle: Force printing title. | |
194 | forcethumbnail: Force printing thumbnail URL. | |
195 | forcedescription: Force printing description. | |
196 | simulate: Do not download the video files. | |
197 | format: Video format code. | |
198 | format_limit: Highest quality format to try. | |
199 | outtmpl: Template for output names. | |
200 | ignoreerrors: Do not stop on download errors. | |
201 | ratelimit: Download speed limit, in bytes/sec. | |
202 | nooverwrites: Prevent overwriting files. | |
203 | retries: Number of times to retry for HTTP error 5xx | |
204 | continuedl: Try to continue downloads if possible. | |
205 | noprogress: Do not print the progress bar. | |
206 | playliststart: Playlist item to start at. | |
8cc44341 | 207 | playlistend: Playlist item to end at. |
331ce0a0 | 208 | logtostderr: Log messages to stderr instead of stdout. |
4fa74b52 RG |
209 | """ |
210 | ||
d0a9affb | 211 | params = None |
4fa74b52 | 212 | _ies = [] |
65cd34c5 | 213 | _pps = [] |
9bf386d7 | 214 | _download_retcode = None |
7d8d0612 | 215 | _num_downloads = None |
331ce0a0 | 216 | _screen_file = None |
4fa74b52 RG |
217 | |
218 | def __init__(self, params): | |
1c5e2302 | 219 | """Create a FileDownloader object with the given options.""" |
4fa74b52 | 220 | self._ies = [] |
65cd34c5 | 221 | self._pps = [] |
9bf386d7 | 222 | self._download_retcode = 0 |
7d8d0612 | 223 | self._num_downloads = 0 |
331ce0a0 | 224 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] |
d0a9affb | 225 | self.params = params |
4fa74b52 RG |
226 | |
227 | @staticmethod | |
228 | def pmkdir(filename): | |
229 | """Create directory components in filename. Similar to Unix "mkdir -p".""" | |
230 | components = filename.split(os.sep) | |
231 | aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))] | |
3af1e172 | 232 | aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator |
4fa74b52 RG |
233 | for dir in aggregate: |
234 | if not os.path.exists(dir): | |
235 | os.mkdir(dir) | |
236 | ||
237 | @staticmethod | |
238 | def format_bytes(bytes): | |
239 | if bytes is None: | |
240 | return 'N/A' | |
8497c36d RG |
241 | if type(bytes) is str: |
242 | bytes = float(bytes) | |
243 | if bytes == 0.0: | |
4fa74b52 RG |
244 | exponent = 0 |
245 | else: | |
8497c36d | 246 | exponent = long(math.log(bytes, 1024.0)) |
4fa74b52 | 247 | suffix = 'bkMGTPEZY'[exponent] |
4fa74b52 RG |
248 | converted = float(bytes) / float(1024**exponent) |
249 | return '%.2f%s' % (converted, suffix) | |
250 | ||
251 | @staticmethod | |
252 | def calc_percent(byte_counter, data_len): | |
253 | if data_len is None: | |
254 | return '---.-%' | |
255 | return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0)) | |
256 | ||
257 | @staticmethod | |
258 | def calc_eta(start, now, total, current): | |
259 | if total is None: | |
260 | return '--:--' | |
261 | dif = now - start | |
262 | if current == 0 or dif < 0.001: # One millisecond | |
263 | return '--:--' | |
264 | rate = float(current) / dif | |
265 | eta = long((float(total) - float(current)) / rate) | |
266 | (eta_mins, eta_secs) = divmod(eta, 60) | |
267 | if eta_mins > 99: | |
268 | return '--:--' | |
269 | return '%02d:%02d' % (eta_mins, eta_secs) | |
270 | ||
5121ef20 | 271 | @staticmethod |
4fa74b52 RG |
272 | def calc_speed(start, now, bytes): |
273 | dif = now - start | |
274 | if bytes == 0 or dif < 0.001: # One millisecond | |
9fcd8355 | 275 | return '%10s' % '---b/s' |
4fa74b52 RG |
276 | return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif)) |
277 | ||
278 | @staticmethod | |
279 | def best_block_size(elapsed_time, bytes): | |
280 | new_min = max(bytes / 2.0, 1.0) | |
281 | new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB | |
282 | if elapsed_time < 0.001: | |
e1f18b8a | 283 | return long(new_max) |
4fa74b52 RG |
284 | rate = bytes / elapsed_time |
285 | if rate > new_max: | |
e1f18b8a | 286 | return long(new_max) |
4fa74b52 | 287 | if rate < new_min: |
e1f18b8a RG |
288 | return long(new_min) |
289 | return long(rate) | |
4fa74b52 | 290 | |
acd3d842 RG |
291 | @staticmethod |
292 | def parse_bytes(bytestr): | |
293 | """Parse a string indicating a byte quantity into a long integer.""" | |
294 | matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) | |
295 | if matchobj is None: | |
296 | return None | |
297 | number = float(matchobj.group(1)) | |
298 | multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) | |
299 | return long(round(number * multiplier)) | |
300 | ||
4fa74b52 RG |
301 | def add_info_extractor(self, ie): |
302 | """Add an InfoExtractor object to the end of the list.""" | |
303 | self._ies.append(ie) | |
304 | ie.set_downloader(self) | |
305 | ||
65cd34c5 RG |
306 | def add_post_processor(self, pp): |
307 | """Add a PostProcessor object to the end of the chain.""" | |
308 | self._pps.append(pp) | |
309 | pp.set_downloader(self) | |
310 | ||
331ce0a0 | 311 | def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False): |
9fcd8355 | 312 | """Print message to stdout if not in quiet mode.""" |
43ab0ca4 RG |
313 | try: |
314 | if not self.params.get('quiet', False): | |
331ce0a0 RG |
315 | terminator = [u'\n', u''][skip_eol] |
316 | print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()), | |
317 | self._screen_file.flush() | |
43ab0ca4 RG |
318 | except (UnicodeEncodeError), err: |
319 | if not ignore_encoding_errors: | |
320 | raise | |
7e5cab67 RG |
321 | |
322 | def to_stderr(self, message): | |
323 | """Print message to stderr.""" | |
eae2666c | 324 | print >>sys.stderr, message.encode(preferredencoding()) |
22899cea RG |
325 | |
326 | def fixed_template(self): | |
327 | """Checks if the output template is fixed.""" | |
d0a9affb | 328 | return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) |
9fcd8355 | 329 | |
0086d1ec RG |
330 | def trouble(self, message=None): |
331 | """Determine action to take when a download problem appears. | |
332 | ||
333 | Depending on if the downloader has been configured to ignore | |
e5bf0f55 | 334 | download errors or not, this method may throw an exception or |
9bf386d7 | 335 | not when errors are found, after printing the message. |
0086d1ec RG |
336 | """ |
337 | if message is not None: | |
338 | self.to_stderr(message) | |
d0a9affb | 339 | if not self.params.get('ignoreerrors', False): |
e5bf0f55 | 340 | raise DownloadError(message) |
9bf386d7 | 341 | self._download_retcode = 1 |
0086d1ec | 342 | |
acd3d842 RG |
343 | def slow_down(self, start_time, byte_counter): |
344 | """Sleep if the download speed is over the rate limit.""" | |
d0a9affb | 345 | rate_limit = self.params.get('ratelimit', None) |
acd3d842 RG |
346 | if rate_limit is None or byte_counter == 0: |
347 | return | |
348 | now = time.time() | |
349 | elapsed = now - start_time | |
350 | if elapsed <= 0.0: | |
351 | return | |
352 | speed = float(byte_counter) / elapsed | |
353 | if speed > rate_limit: | |
354 | time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) | |
355 | ||
bafa5cd9 RG |
356 | def report_destination(self, filename): |
357 | """Report destination filename.""" | |
331ce0a0 | 358 | self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) |
bafa5cd9 RG |
359 | |
360 | def report_progress(self, percent_str, data_len_str, speed_str, eta_str): | |
361 | """Report download progress.""" | |
d9835247 RG |
362 | if self.params.get('noprogress', False): |
363 | return | |
331ce0a0 | 364 | self.to_screen(u'\r[download] %s of %s at %s ETA %s' % |
bafa5cd9 | 365 | (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) |
7db85b2c RG |
366 | |
367 | def report_resuming_byte(self, resume_len): | |
8a9f53be | 368 | """Report attempt to resume at given byte.""" |
331ce0a0 | 369 | self.to_screen(u'[download] Resuming download at byte %s' % resume_len) |
7db85b2c | 370 | |
7031008c | 371 | def report_retry(self, count, retries): |
e86e9474 | 372 | """Report retry in case of HTTP error 5xx""" |
331ce0a0 | 373 | self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) |
7031008c | 374 | |
7db85b2c RG |
375 | def report_file_already_downloaded(self, file_name): |
376 | """Report file has already been fully downloaded.""" | |
43ab0ca4 | 377 | try: |
331ce0a0 | 378 | self.to_screen(u'[download] %s has already been downloaded' % file_name) |
43ab0ca4 | 379 | except (UnicodeEncodeError), err: |
331ce0a0 | 380 | self.to_screen(u'[download] The file has already been downloaded') |
7db85b2c RG |
381 | |
382 | def report_unable_to_resume(self): | |
383 | """Report it was impossible to resume download.""" | |
331ce0a0 | 384 | self.to_screen(u'[download] Unable to resume') |
bafa5cd9 RG |
385 | |
386 | def report_finish(self): | |
387 | """Report download finished.""" | |
d9835247 | 388 | if self.params.get('noprogress', False): |
331ce0a0 | 389 | self.to_screen(u'[download] Download completed') |
d9835247 | 390 | else: |
331ce0a0 | 391 | self.to_screen(u'') |
df372a65 RG |
392 | |
393 | def increment_downloads(self): | |
394 | """Increment the ordinal that assigns a number to each file.""" | |
395 | self._num_downloads += 1 | |
bafa5cd9 | 396 | |
c8619e01 RG |
397 | def process_info(self, info_dict): |
398 | """Process a single dictionary returned by an InfoExtractor.""" | |
c8619e01 RG |
399 | # Do nothing else if in simulate mode |
400 | if self.params.get('simulate', False): | |
cbfff4db RG |
401 | # Forced printings |
402 | if self.params.get('forcetitle', False): | |
490fd7ae | 403 | print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') |
cbfff4db | 404 | if self.params.get('forceurl', False): |
490fd7ae | 405 | print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') |
7e58d568 RG |
406 | if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: |
407 | print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') | |
408 | if self.params.get('forcedescription', False) and 'description' in info_dict: | |
409 | print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') | |
cbfff4db | 410 | |
9bf386d7 | 411 | return |
cbfff4db | 412 | |
c8619e01 | 413 | try: |
ad274509 RG |
414 | template_dict = dict(info_dict) |
415 | template_dict['epoch'] = unicode(long(time.time())) | |
1e47d226 | 416 | template_dict['autonumber'] = unicode('%05d' % self._num_downloads) |
ad274509 | 417 | filename = self.params['outtmpl'] % template_dict |
c8619e01 | 418 | except (ValueError, KeyError), err: |
38ed1344 RG |
419 | self.trouble(u'ERROR: invalid system charset or erroneous output template') |
420 | return | |
850ab765 | 421 | if self.params.get('nooverwrites', False) and os.path.exists(filename): |
5c44af18 | 422 | self.to_stderr(u'WARNING: file exists and will be skipped') |
9bf386d7 | 423 | return |
7b7759f5 | 424 | |
c8619e01 RG |
425 | try: |
426 | self.pmkdir(filename) | |
427 | except (OSError, IOError), err: | |
db7e31b8 | 428 | self.trouble(u'ERROR: unable to create directories: %s' % str(err)) |
9bf386d7 | 429 | return |
7b7759f5 | 430 | |
c8619e01 | 431 | try: |
e616ec0c | 432 | success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None)) |
c8619e01 | 433 | except (OSError, IOError), err: |
73f4e7af | 434 | raise UnavailableVideoError |
c8619e01 | 435 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
db7e31b8 | 436 | self.trouble(u'ERROR: unable to download video data: %s' % str(err)) |
9bf386d7 | 437 | return |
d69a1c91 | 438 | except (ContentTooShortError, ), err: |
db7e31b8 | 439 | self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) |
d69a1c91 | 440 | return |
7b7759f5 | 441 | |
55e7c75e RG |
442 | if success: |
443 | try: | |
444 | self.post_process(filename, info_dict) | |
445 | except (PostProcessingError), err: | |
db7e31b8 | 446 | self.trouble(u'ERROR: postprocessing: %s' % str(err)) |
55e7c75e | 447 | return |
c8619e01 | 448 | |
4fa74b52 RG |
449 | def download(self, url_list): |
450 | """Download a given list of URLs.""" | |
22899cea | 451 | if len(url_list) > 1 and self.fixed_template(): |
d0a9affb | 452 | raise SameFileError(self.params['outtmpl']) |
22899cea | 453 | |
4fa74b52 RG |
454 | for url in url_list: |
455 | suitable_found = False | |
456 | for ie in self._ies: | |
c8619e01 | 457 | # Go to next InfoExtractor if not suitable |
4fa74b52 RG |
458 | if not ie.suitable(url): |
459 | continue | |
c8619e01 | 460 | |
4fa74b52 RG |
461 | # Suitable InfoExtractor found |
462 | suitable_found = True | |
c8619e01 | 463 | |
6f21f686 RG |
464 | # Extract information from URL and process it |
465 | ie.extract(url) | |
65cd34c5 | 466 | |
c8619e01 | 467 | # Suitable InfoExtractor had been found; go to next URL |
4fa74b52 | 468 | break |
c8619e01 | 469 | |
4fa74b52 | 470 | if not suitable_found: |
db7e31b8 | 471 | self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) |
bb681b88 | 472 | |
9bf386d7 | 473 | return self._download_retcode |
65cd34c5 RG |
474 | |
475 | def post_process(self, filename, ie_info): | |
476 | """Run the postprocessing chain on the given file.""" | |
477 | info = dict(ie_info) | |
478 | info['filepath'] = filename | |
479 | for pp in self._pps: | |
480 | info = pp.run(info) | |
481 | if info is None: | |
482 | break | |
4fa74b52 | 483 | |
e616ec0c | 484 | def _download_with_rtmpdump(self, filename, url, player_url): |
0487b407 RG |
485 | self.report_destination(filename) |
486 | ||
487 | # Check for rtmpdump first | |
488 | try: | |
489 | subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT) | |
490 | except (OSError, IOError): | |
491 | self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run') | |
492 | return False | |
493 | ||
494 | # Download using rtmpdump. rtmpdump returns exit code 2 when | |
495 | # the connection was interrumpted and resuming appears to be | |
496 | # possible. This is part of rtmpdump's normal usage, AFAIK. | |
e616ec0c | 497 | basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename] |
1c1821f8 RG |
498 | retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) |
499 | while retval == 2 or retval == 1: | |
e616ec0c | 500 | prevsize = os.path.getsize(filename) |
331ce0a0 | 501 | self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) |
e616ec0c | 502 | time.sleep(5.0) # This seems to be needed |
1c1821f8 | 503 | retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) |
e616ec0c RG |
504 | cursize = os.path.getsize(filename) |
505 | if prevsize == cursize and retval == 1: | |
506 | break | |
0487b407 | 507 | if retval == 0: |
331ce0a0 | 508 | self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename)) |
0487b407 RG |
509 | return True |
510 | else: | |
db7e31b8 | 511 | self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) |
0487b407 RG |
512 | return False |
513 | ||
e616ec0c | 514 | def _do_download(self, filename, url, player_url): |
0487b407 RG |
515 | # Attempt to download using rtmpdump |
516 | if url.startswith('rtmp'): | |
e616ec0c | 517 | return self._download_with_rtmpdump(filename, url, player_url) |
0487b407 | 518 | |
55e7c75e | 519 | stream = None |
9c457d2a | 520 | open_mode = 'wb' |
7db85b2c | 521 | basic_request = urllib2.Request(url, None, std_headers) |
4fa74b52 | 522 | request = urllib2.Request(url, None, std_headers) |
7db85b2c | 523 | |
9c457d2a | 524 | # Establish possible resume length |
55e7c75e RG |
525 | if os.path.isfile(filename): |
526 | resume_len = os.path.getsize(filename) | |
527 | else: | |
528 | resume_len = 0 | |
9c457d2a RG |
529 | |
530 | # Request parameters in case of being able to resume | |
850ab765 | 531 | if self.params.get('continuedl', False) and resume_len != 0: |
7db85b2c RG |
532 | self.report_resuming_byte(resume_len) |
533 | request.add_header('Range','bytes=%d-' % resume_len) | |
9c457d2a | 534 | open_mode = 'ab' |
55e7c75e | 535 | |
7031008c RG |
536 | count = 0 |
537 | retries = self.params.get('retries', 0) | |
101e0d1e | 538 | while count <= retries: |
7031008c RG |
539 | # Establish connection |
540 | try: | |
541 | data = urllib2.urlopen(request) | |
542 | break | |
543 | except (urllib2.HTTPError, ), err: | |
ac249f42 | 544 | if (err.code < 500 or err.code >= 600) and err.code != 416: |
101e0d1e | 545 | # Unexpected HTTP error |
7031008c | 546 | raise |
101e0d1e RG |
547 | elif err.code == 416: |
548 | # Unable to resume (requested range not satisfiable) | |
549 | try: | |
550 | # Open the connection again without the range header | |
551 | data = urllib2.urlopen(basic_request) | |
552 | content_length = data.info()['Content-Length'] | |
553 | except (urllib2.HTTPError, ), err: | |
ac249f42 | 554 | if err.code < 500 or err.code >= 600: |
101e0d1e RG |
555 | raise |
556 | else: | |
557 | # Examine the reported length | |
268fb2bd | 558 | if (content_length is not None and |
204c9398 | 559 | (resume_len - 100 < long(content_length) < resume_len + 100)): |
268fb2bd RG |
560 | # The file had already been fully downloaded. |
561 | # Explanation to the above condition: in issue #175 it was revealed that | |
562 | # YouTube sometimes adds or removes a few bytes from the end of the file, | |
563 | # changing the file size slightly and causing problems for some users. So | |
564 | # I decided to implement a suggested change and consider the file | |
565 | # completely downloaded if the file size differs less than 100 bytes from | |
566 | # the one in the hard drive. | |
101e0d1e RG |
567 | self.report_file_already_downloaded(filename) |
568 | return True | |
569 | else: | |
570 | # The length does not match, we start the download over | |
571 | self.report_unable_to_resume() | |
572 | open_mode = 'wb' | |
573 | break | |
574 | # Retry | |
575 | count += 1 | |
576 | if count <= retries: | |
577 | self.report_retry(count, retries) | |
578 | ||
579 | if count > retries: | |
580 | self.trouble(u'ERROR: giving up after %s retries' % retries) | |
581 | return False | |
7db85b2c | 582 | |
4fa74b52 RG |
583 | data_len = data.info().get('Content-length', None) |
584 | data_len_str = self.format_bytes(data_len) | |
585 | byte_counter = 0 | |
586 | block_size = 1024 | |
587 | start = time.time() | |
588 | while True: | |
bafa5cd9 | 589 | # Download and write |
4fa74b52 RG |
590 | before = time.time() |
591 | data_block = data.read(block_size) | |
592 | after = time.time() | |
593 | data_block_len = len(data_block) | |
594 | if data_block_len == 0: | |
595 | break | |
596 | byte_counter += data_block_len | |
55e7c75e RG |
597 | |
598 | # Open file just in time | |
599 | if stream is None: | |
600 | try: | |
31bcb480 | 601 | (stream, filename) = sanitize_open(filename, open_mode) |
55e7c75e RG |
602 | self.report_destination(filename) |
603 | except (OSError, IOError), err: | |
db7e31b8 | 604 | self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) |
55e7c75e | 605 | return False |
131efd1a RG |
606 | try: |
607 | stream.write(data_block) | |
608 | except (IOError, OSError), err: | |
d67e0974 RG |
609 | self.trouble(u'\nERROR: unable to write data: %s' % str(err)) |
610 | return False | |
4fa74b52 RG |
611 | block_size = self.best_block_size(after - before, data_block_len) |
612 | ||
55e7c75e RG |
613 | # Progress message |
614 | percent_str = self.calc_percent(byte_counter, data_len) | |
615 | eta_str = self.calc_eta(start, time.time(), data_len, byte_counter) | |
616 | speed_str = self.calc_speed(start, time.time(), byte_counter) | |
617 | self.report_progress(percent_str, data_len_str, speed_str, eta_str) | |
618 | ||
acd3d842 RG |
619 | # Apply rate limit |
620 | self.slow_down(start, byte_counter) | |
621 | ||
bafa5cd9 | 622 | self.report_finish() |
4fa74b52 | 623 | if data_len is not None and str(byte_counter) != data_len: |
d69a1c91 | 624 | raise ContentTooShortError(byte_counter, long(data_len)) |
55e7c75e | 625 | return True |
4fa74b52 RG |
626 | |
627 | class InfoExtractor(object): | |
628 | """Information Extractor class. | |
629 | ||
630 | Information extractors are the classes that, given a URL, extract | |
631 | information from the video (or videos) the URL refers to. This | |
632 | information includes the real video URL, the video title and simplified | |
2851b2ca RG |
633 | title, author and others. The information is stored in a dictionary |
634 | which is then passed to the FileDownloader. The FileDownloader | |
635 | processes this information possibly downloading the video to the file | |
636 | system, among other possible outcomes. The dictionaries must include | |
4fa74b52 RG |
637 | the following fields: |
638 | ||
639 | id: Video identifier. | |
640 | url: Final video URL. | |
641 | uploader: Nickname of the video uploader. | |
642 | title: Literal title. | |
643 | stitle: Simplified title. | |
644 | ext: Video filename extension. | |
6ba562b0 | 645 | format: Video format. |
e616ec0c | 646 | player_url: SWF Player URL (may be None). |
4fa74b52 | 647 | |
7e58d568 RG |
648 | The following fields are optional. Their primary purpose is to allow |
649 | youtube-dl to serve as the backend for a video search function, such | |
650 | as the one in youtube2mp3. They are only used when their respective | |
651 | forced printing functions are called: | |
652 | ||
653 | thumbnail: Full URL to a video thumbnail image. | |
654 | description: One-line video description. | |
655 | ||
4fa74b52 RG |
656 | Subclasses of this one should re-define the _real_initialize() and |
657 | _real_extract() methods, as well as the suitable() static method. | |
658 | Probably, they should also be instantiated and added to the main | |
659 | downloader. | |
660 | """ | |
661 | ||
662 | _ready = False | |
663 | _downloader = None | |
664 | ||
665 | def __init__(self, downloader=None): | |
666 | """Constructor. Receives an optional downloader.""" | |
667 | self._ready = False | |
668 | self.set_downloader(downloader) | |
669 | ||
670 | @staticmethod | |
671 | def suitable(url): | |
672 | """Receives a URL and returns True if suitable for this IE.""" | |
020f7150 | 673 | return False |
4fa74b52 RG |
674 | |
675 | def initialize(self): | |
1c5e2302 | 676 | """Initializes an instance (authentication, etc).""" |
4fa74b52 RG |
677 | if not self._ready: |
678 | self._real_initialize() | |
679 | self._ready = True | |
680 | ||
681 | def extract(self, url): | |
682 | """Extracts URL information and returns it in list of dicts.""" | |
683 | self.initialize() | |
684 | return self._real_extract(url) | |
685 | ||
686 | def set_downloader(self, downloader): | |
687 | """Sets the downloader for this IE.""" | |
688 | self._downloader = downloader | |
689 | ||
4fa74b52 RG |
690 | def _real_initialize(self): |
691 | """Real initialization process. Redefine in subclasses.""" | |
692 | pass | |
693 | ||
694 | def _real_extract(self, url): | |
695 | """Real extraction process. Redefine in subclasses.""" | |
696 | pass | |
697 | ||
698 | class YoutubeIE(InfoExtractor): | |
699 | """Information extractor for youtube.com.""" | |
700 | ||
a949a3ae | 701 | _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' |
9715661c | 702 | _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' |
7df4635f | 703 | _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' |
72ac78b8 | 704 | _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' |
4fa74b52 | 705 | _NETRC_MACHINE = 'youtube' |
497cd3e6 RG |
706 | # Listed in order of quality |
707 | _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13'] | |
7b7759f5 | 708 | _video_extensions = { |
709 | '13': '3gp', | |
710 | '17': 'mp4', | |
711 | '18': 'mp4', | |
712 | '22': 'mp4', | |
d9bc015b | 713 | '37': 'mp4', |
9e9647d9 | 714 | '38': 'video', # You actually don't know if this will be MOV, AVI or whatever |
0b59bf4a RG |
715 | '43': 'webm', |
716 | '45': 'webm', | |
7b7759f5 | 717 | } |
4fa74b52 | 718 | |
020f7150 RG |
719 | @staticmethod |
720 | def suitable(url): | |
721 | return (re.match(YoutubeIE._VALID_URL, url) is not None) | |
722 | ||
72ac78b8 RG |
723 | def report_lang(self): |
724 | """Report attempt to set language.""" | |
331ce0a0 | 725 | self._downloader.to_screen(u'[youtube] Setting language') |
72ac78b8 | 726 | |
bafa5cd9 RG |
727 | def report_login(self): |
728 | """Report attempt to log in.""" | |
331ce0a0 | 729 | self._downloader.to_screen(u'[youtube] Logging in') |
bafa5cd9 RG |
730 | |
731 | def report_age_confirmation(self): | |
732 | """Report attempt to confirm age.""" | |
331ce0a0 | 733 | self._downloader.to_screen(u'[youtube] Confirming age') |
bafa5cd9 | 734 | |
e616ec0c RG |
735 | def report_video_webpage_download(self, video_id): |
736 | """Report attempt to download video webpage.""" | |
331ce0a0 | 737 | self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id) |
e616ec0c | 738 | |
71b7300e RG |
739 | def report_video_info_webpage_download(self, video_id): |
740 | """Report attempt to download video info webpage.""" | |
331ce0a0 | 741 | self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) |
bafa5cd9 RG |
742 | |
743 | def report_information_extraction(self, video_id): | |
744 | """Report attempt to extract video information.""" | |
331ce0a0 | 745 | self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) |
bafa5cd9 | 746 | |
7b7759f5 | 747 | def report_unavailable_format(self, video_id, format): |
748 | """Report extracted video URL.""" | |
331ce0a0 | 749 | self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) |
7b7759f5 | 750 | |
0487b407 RG |
751 | def report_rtmp_download(self): |
752 | """Indicate the download will use the RTMP protocol.""" | |
331ce0a0 | 753 | self._downloader.to_screen(u'[youtube] RTMP download detected') |
0487b407 | 754 | |
4fa74b52 RG |
755 | def _real_initialize(self): |
756 | if self._downloader is None: | |
757 | return | |
758 | ||
759 | username = None | |
760 | password = None | |
d0a9affb | 761 | downloader_params = self._downloader.params |
4fa74b52 RG |
762 | |
763 | # Attempt to use provided username and password or .netrc data | |
764 | if downloader_params.get('username', None) is not None: | |
765 | username = downloader_params['username'] | |
766 | password = downloader_params['password'] | |
767 | elif downloader_params.get('usenetrc', False): | |
768 | try: | |
769 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
770 | if info is not None: | |
771 | username = info[0] | |
772 | password = info[2] | |
773 | else: | |
774 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
775 | except (IOError, netrc.NetrcParseError), err: | |
6f21f686 | 776 | self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) |
4fa74b52 RG |
777 | return |
778 | ||
72ac78b8 | 779 | # Set language |
cc109403 | 780 | request = urllib2.Request(self._LANG_URL, None, std_headers) |
72ac78b8 RG |
781 | try: |
782 | self.report_lang() | |
783 | urllib2.urlopen(request).read() | |
784 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
6f21f686 | 785 | self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err)) |
72ac78b8 RG |
786 | return |
787 | ||
cc109403 RG |
788 | # No authentication to be performed |
789 | if username is None: | |
790 | return | |
791 | ||
4fa74b52 | 792 | # Log in |
9fcd8355 RG |
793 | login_form = { |
794 | 'current_form': 'loginForm', | |
4fa74b52 RG |
795 | 'next': '/', |
796 | 'action_login': 'Log In', | |
797 | 'username': username, | |
9fcd8355 RG |
798 | 'password': password, |
799 | } | |
4fa74b52 RG |
800 | request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) |
801 | try: | |
bafa5cd9 | 802 | self.report_login() |
4fa74b52 RG |
803 | login_results = urllib2.urlopen(request).read() |
804 | if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: | |
6f21f686 | 805 | self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password') |
4fa74b52 RG |
806 | return |
807 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
6f21f686 | 808 | self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err)) |
4fa74b52 RG |
809 | return |
810 | ||
811 | # Confirm age | |
9fcd8355 RG |
812 | age_form = { |
813 | 'next_url': '/', | |
814 | 'action_confirm': 'Confirm', | |
815 | } | |
4fa74b52 RG |
816 | request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers) |
817 | try: | |
bafa5cd9 | 818 | self.report_age_confirmation() |
4fa74b52 RG |
819 | age_results = urllib2.urlopen(request).read() |
820 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 821 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) |
e5bf0f55 | 822 | return |
4fa74b52 RG |
823 | |
824 | def _real_extract(self, url): | |
825 | # Extract video id from URL | |
020f7150 | 826 | mobj = re.match(self._VALID_URL, url) |
4fa74b52 | 827 | if mobj is None: |
147753eb | 828 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) |
6f21f686 | 829 | return |
4fa74b52 RG |
830 | video_id = mobj.group(2) |
831 | ||
497cd3e6 RG |
832 | # Get video webpage |
833 | self.report_video_webpage_download(video_id) | |
834 | request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers) | |
835 | try: | |
836 | video_webpage = urllib2.urlopen(request).read() | |
837 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
838 | self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) | |
839 | return | |
968aa884 | 840 | |
497cd3e6 RG |
841 | # Attempt to extract SWF player URL |
842 | mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage) | |
843 | if mobj is not None: | |
844 | player_url = mobj.group(1) | |
845 | else: | |
846 | player_url = None | |
847 | ||
848 | # Get video info | |
849 | self.report_video_info_webpage_download(video_id) | |
850 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
851 | video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
852 | % (video_id, el_type)) | |
853 | request = urllib2.Request(video_info_url, None, std_headers) | |
e616ec0c | 854 | try: |
497cd3e6 RG |
855 | video_info_webpage = urllib2.urlopen(request).read() |
856 | video_info = parse_qs(video_info_webpage) | |
857 | if 'token' in video_info: | |
858 | break | |
e616ec0c | 859 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: |
497cd3e6 | 860 | self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) |
e616ec0c | 861 | return |
f95f29fd RG |
862 | if 'token' not in video_info: |
863 | if 'reason' in video_info: | |
8e686771 | 864 | self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8')) |
f95f29fd RG |
865 | else: |
866 | self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') | |
867 | return | |
868 | ||
869 | # Start extracting information | |
497cd3e6 RG |
870 | self.report_information_extraction(video_id) |
871 | ||
872 | # uploader | |
873 | if 'author' not in video_info: | |
874 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
875 | return | |
876 | video_uploader = urllib.unquote_plus(video_info['author'][0]) | |
e616ec0c | 877 | |
497cd3e6 RG |
878 | # title |
879 | if 'title' not in video_info: | |
880 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
881 | return | |
882 | video_title = urllib.unquote_plus(video_info['title'][0]) | |
883 | video_title = video_title.decode('utf-8') | |
884 | video_title = sanitize_title(video_title) | |
885 | ||
886 | # simplified title | |
887 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
888 | simple_title = simple_title.strip(ur'_') | |
889 | ||
890 | # thumbnail image | |
891 | if 'thumbnail_url' not in video_info: | |
892 | self._downloader.trouble(u'WARNING: unable to extract video thumbnail') | |
893 | video_thumbnail = '' | |
894 | else: # don't panic if we can't find it | |
895 | video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) | |
896 | ||
897 | # description | |
898 | video_description = 'No description available.' | |
899 | if self._downloader.params.get('forcedescription', False): | |
900 | mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage) | |
e616ec0c | 901 | if mobj is not None: |
497cd3e6 RG |
902 | video_description = mobj.group(1) |
903 | ||
5ce7d172 RG |
904 | # token |
905 | video_token = urllib.unquote_plus(video_info['token'][0]) | |
906 | ||
497cd3e6 | 907 | # Decide which formats to download |
2e3a32e4 | 908 | requested_format = self._downloader.params.get('format', None) |
5ce7d172 | 909 | get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token) |
2e3a32e4 | 910 | |
5ce7d172 | 911 | if 'fmt_url_map' in video_info: |
497cd3e6 RG |
912 | url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(',')) |
913 | format_limit = self._downloader.params.get('format_limit', None) | |
914 | if format_limit is not None and format_limit in self._available_formats: | |
915 | format_list = self._available_formats[self._available_formats.index(format_limit):] | |
e616ec0c | 916 | else: |
497cd3e6 RG |
917 | format_list = self._available_formats |
918 | existing_formats = [x for x in format_list if x in url_map] | |
919 | if len(existing_formats) == 0: | |
920 | self._downloader.trouble(u'ERROR: no known formats available for video') | |
968aa884 | 921 | return |
497cd3e6 | 922 | if requested_format is None: |
5ce7d172 | 923 | video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality |
497cd3e6 | 924 | elif requested_format == '-1': |
5ce7d172 | 925 | video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats |
497cd3e6 | 926 | else: |
5ce7d172 | 927 | video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format |
2e3a32e4 | 928 | |
497cd3e6 RG |
929 | elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
930 | self.report_rtmp_download() | |
931 | video_url_list = [(None, video_info['conn'][0])] | |
2e3a32e4 | 932 | |
497cd3e6 RG |
933 | else: |
934 | self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info') | |
935 | return | |
7b7759f5 | 936 | |
497cd3e6 RG |
937 | for format_param, video_real_url in video_url_list: |
938 | # At this point we have a new video | |
939 | self._downloader.increment_downloads() | |
940 | ||
941 | # Extension | |
942 | video_extension = self._video_extensions.get(format_param, 'flv') | |
7e58d568 | 943 | |
497cd3e6 | 944 | # Find the video URL in fmt_url_map or conn paramters |
968aa884 | 945 | try: |
7b7759f5 | 946 | # Process video information |
947 | self._downloader.process_info({ | |
948 | 'id': video_id.decode('utf-8'), | |
949 | 'url': video_real_url.decode('utf-8'), | |
950 | 'uploader': video_uploader.decode('utf-8'), | |
951 | 'title': video_title, | |
952 | 'stitle': simple_title, | |
953 | 'ext': video_extension.decode('utf-8'), | |
6ba562b0 | 954 | 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), |
7e58d568 RG |
955 | 'thumbnail': video_thumbnail.decode('utf-8'), |
956 | 'description': video_description.decode('utf-8'), | |
e616ec0c | 957 | 'player_url': player_url, |
7b7759f5 | 958 | }) |
497cd3e6 | 959 | except UnavailableVideoError, err: |
5ce7d172 | 960 | self._downloader.trouble(u'ERROR: unable to download video (format may not be available)') |
42bcd27d | 961 | |
4fa74b52 | 962 | |
020f7150 RG |
963 | class MetacafeIE(InfoExtractor): |
964 | """Information Extractor for metacafe.com.""" | |
965 | ||
966 | _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' | |
2546e767 | 967 | _DISCLAIMER = 'http://www.metacafe.com/family_filter/' |
dbccb6cd | 968 | _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' |
020f7150 RG |
969 | _youtube_ie = None |
970 | ||
971 | def __init__(self, youtube_ie, downloader=None): | |
972 | InfoExtractor.__init__(self, downloader) | |
973 | self._youtube_ie = youtube_ie | |
974 | ||
975 | @staticmethod | |
976 | def suitable(url): | |
977 | return (re.match(MetacafeIE._VALID_URL, url) is not None) | |
978 | ||
979 | def report_disclaimer(self): | |
980 | """Report disclaimer retrieval.""" | |
331ce0a0 | 981 | self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') |
020f7150 RG |
982 | |
983 | def report_age_confirmation(self): | |
984 | """Report attempt to confirm age.""" | |
331ce0a0 | 985 | self._downloader.to_screen(u'[metacafe] Confirming age') |
020f7150 RG |
986 | |
987 | def report_download_webpage(self, video_id): | |
988 | """Report webpage download.""" | |
331ce0a0 | 989 | self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) |
020f7150 RG |
990 | |
991 | def report_extraction(self, video_id): | |
992 | """Report information extraction.""" | |
331ce0a0 | 993 | self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) |
020f7150 RG |
994 | |
995 | def _real_initialize(self): | |
996 | # Retrieve disclaimer | |
997 | request = urllib2.Request(self._DISCLAIMER, None, std_headers) | |
998 | try: | |
999 | self.report_disclaimer() | |
1000 | disclaimer = urllib2.urlopen(request).read() | |
1001 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1002 | self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err)) |
020f7150 RG |
1003 | return |
1004 | ||
1005 | # Confirm age | |
1006 | disclaimer_form = { | |
2546e767 | 1007 | 'filters': '0', |
020f7150 RG |
1008 | 'submit': "Continue - I'm over 18", |
1009 | } | |
dbccb6cd | 1010 | request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers) |
020f7150 RG |
1011 | try: |
1012 | self.report_age_confirmation() | |
1013 | disclaimer = urllib2.urlopen(request).read() | |
1014 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1015 | self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err)) |
020f7150 RG |
1016 | return |
1017 | ||
1018 | def _real_extract(self, url): | |
1019 | # Extract id and simplified title from URL | |
1020 | mobj = re.match(self._VALID_URL, url) | |
1021 | if mobj is None: | |
147753eb | 1022 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) |
6f21f686 | 1023 | return |
020f7150 RG |
1024 | |
1025 | video_id = mobj.group(1) | |
1026 | ||
1027 | # Check if video comes from YouTube | |
1028 | mobj2 = re.match(r'^yt-(.*)$', video_id) | |
1029 | if mobj2 is not None: | |
6f21f686 RG |
1030 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) |
1031 | return | |
020f7150 | 1032 | |
df372a65 | 1033 | # At this point we have a new video |
9bf7fa52 | 1034 | self._downloader.increment_downloads() |
df372a65 | 1035 | |
020f7150 | 1036 | simple_title = mobj.group(2).decode('utf-8') |
020f7150 RG |
1037 | |
1038 | # Retrieve video webpage to extract further information | |
1039 | request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) | |
1040 | try: | |
1041 | self.report_download_webpage(video_id) | |
1042 | webpage = urllib2.urlopen(request).read() | |
1043 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1044 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) |
6f21f686 | 1045 | return |
020f7150 RG |
1046 | |
1047 | # Extract URL, uploader and title from webpage | |
1048 | self.report_extraction(video_id) | |
18963a36 | 1049 | mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) |
c6c555cf RG |
1050 | if mobj is not None: |
1051 | mediaURL = urllib.unquote(mobj.group(1)) | |
6b57e8c5 | 1052 | video_extension = mediaURL[-3:] |
c6c555cf RG |
1053 | |
1054 | # Extract gdaKey if available | |
1055 | mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) | |
1056 | if mobj is None: | |
1057 | video_url = mediaURL | |
1058 | else: | |
1059 | gdaKey = mobj.group(1) | |
1060 | video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) | |
109626fc | 1061 | else: |
c6c555cf RG |
1062 | mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) |
1063 | if mobj is None: | |
1064 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1065 | return | |
1066 | vardict = parse_qs(mobj.group(1)) | |
1067 | if 'mediaData' not in vardict: | |
1068 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1069 | return | |
1070 | mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) | |
1071 | if mobj is None: | |
1072 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1073 | return | |
6b57e8c5 RG |
1074 | mediaURL = mobj.group(1).replace('\\/', '/') |
1075 | video_extension = mediaURL[-3:] | |
1076 | video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) | |
020f7150 | 1077 | |
2546e767 | 1078 | mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) |
020f7150 | 1079 | if mobj is None: |
147753eb | 1080 | self._downloader.trouble(u'ERROR: unable to extract title') |
6f21f686 | 1081 | return |
020f7150 | 1082 | video_title = mobj.group(1).decode('utf-8') |
490fd7ae | 1083 | video_title = sanitize_title(video_title) |
020f7150 | 1084 | |
29f07568 | 1085 | mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage) |
020f7150 | 1086 | if mobj is None: |
147753eb | 1087 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') |
6f21f686 | 1088 | return |
dbccb6cd | 1089 | video_uploader = mobj.group(1) |
020f7150 | 1090 | |
42bcd27d | 1091 | try: |
1092 | # Process video information | |
1093 | self._downloader.process_info({ | |
1094 | 'id': video_id.decode('utf-8'), | |
1095 | 'url': video_url.decode('utf-8'), | |
1096 | 'uploader': video_uploader.decode('utf-8'), | |
1097 | 'title': video_title, | |
1098 | 'stitle': simple_title, | |
1099 | 'ext': video_extension.decode('utf-8'), | |
6ba562b0 | 1100 | 'format': u'NA', |
e616ec0c | 1101 | 'player_url': None, |
42bcd27d | 1102 | }) |
73f4e7af RG |
1103 | except UnavailableVideoError: |
1104 | self._downloader.trouble(u'ERROR: unable to download video') | |
020f7150 | 1105 | |
25af2bce | 1106 | |
4135fa45 WB |
1107 | class DailymotionIE(InfoExtractor): |
1108 | """Information Extractor for Dailymotion""" | |
1109 | ||
1110 | _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' | |
4135fa45 WB |
1111 | |
1112 | def __init__(self, downloader=None): | |
1113 | InfoExtractor.__init__(self, downloader) | |
1114 | ||
1115 | @staticmethod | |
1116 | def suitable(url): | |
1117 | return (re.match(DailymotionIE._VALID_URL, url) is not None) | |
1118 | ||
4135fa45 WB |
1119 | def report_download_webpage(self, video_id): |
1120 | """Report webpage download.""" | |
331ce0a0 | 1121 | self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id) |
4135fa45 WB |
1122 | |
1123 | def report_extraction(self, video_id): | |
1124 | """Report information extraction.""" | |
331ce0a0 | 1125 | self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) |
4135fa45 WB |
1126 | |
1127 | def _real_initialize(self): | |
1128 | return | |
1129 | ||
4135fa45 WB |
1130 | def _real_extract(self, url): |
1131 | # Extract id and simplified title from URL | |
1132 | mobj = re.match(self._VALID_URL, url) | |
1133 | if mobj is None: | |
1134 | self._downloader.trouble(u'ERROR: invalid URL: %s' % url) | |
1135 | return | |
1136 | ||
df372a65 | 1137 | # At this point we have a new video |
9bf7fa52 | 1138 | self._downloader.increment_downloads() |
4135fa45 WB |
1139 | video_id = mobj.group(1) |
1140 | ||
1141 | simple_title = mobj.group(2).decode('utf-8') | |
1142 | video_extension = 'flv' | |
1143 | ||
1144 | # Retrieve video webpage to extract further information | |
1145 | request = urllib2.Request(url) | |
1146 | try: | |
1147 | self.report_download_webpage(video_id) | |
1148 | webpage = urllib2.urlopen(request).read() | |
1149 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1150 | self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) | |
1151 | return | |
1152 | ||
1153 | # Extract URL, uploader and title from webpage | |
1154 | self.report_extraction(video_id) | |
1155 | mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage) | |
1156 | if mobj is None: | |
1157 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1158 | return | |
1159 | mediaURL = urllib.unquote(mobj.group(1)) | |
1160 | ||
1161 | # if needed add http://www.dailymotion.com/ if relative URL | |
1162 | ||
1163 | video_url = mediaURL | |
1164 | ||
1165 | # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>' | |
1166 | mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage) | |
1167 | if mobj is None: | |
1168 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1169 | return | |
1170 | video_title = mobj.group(1).decode('utf-8') | |
1171 | video_title = sanitize_title(video_title) | |
1172 | ||
33407be7 | 1173 | mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage) |
4135fa45 WB |
1174 | if mobj is None: |
1175 | self._downloader.trouble(u'ERROR: unable to extract uploader nickname') | |
1176 | return | |
1177 | video_uploader = mobj.group(1) | |
1178 | ||
1179 | try: | |
1180 | # Process video information | |
1181 | self._downloader.process_info({ | |
1182 | 'id': video_id.decode('utf-8'), | |
1183 | 'url': video_url.decode('utf-8'), | |
1184 | 'uploader': video_uploader.decode('utf-8'), | |
1185 | 'title': video_title, | |
1186 | 'stitle': simple_title, | |
1187 | 'ext': video_extension.decode('utf-8'), | |
1188 | 'format': u'NA', | |
1189 | 'player_url': None, | |
1190 | }) | |
73f4e7af RG |
1191 | except UnavailableVideoError: |
1192 | self._downloader.trouble(u'ERROR: unable to download video') | |
4135fa45 | 1193 | |
49c0028a | 1194 | class GoogleIE(InfoExtractor): |
1195 | """Information extractor for video.google.com.""" | |
1196 | ||
490fd7ae | 1197 | _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' |
49c0028a | 1198 | |
1199 | def __init__(self, downloader=None): | |
1200 | InfoExtractor.__init__(self, downloader) | |
1201 | ||
1202 | @staticmethod | |
1203 | def suitable(url): | |
1204 | return (re.match(GoogleIE._VALID_URL, url) is not None) | |
1205 | ||
1206 | def report_download_webpage(self, video_id): | |
1207 | """Report webpage download.""" | |
331ce0a0 | 1208 | self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) |
49c0028a | 1209 | |
1210 | def report_extraction(self, video_id): | |
1211 | """Report information extraction.""" | |
331ce0a0 | 1212 | self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) |
49c0028a | 1213 | |
1214 | def _real_initialize(self): | |
1215 | return | |
1216 | ||
1217 | def _real_extract(self, url): | |
1218 | # Extract id from URL | |
1219 | mobj = re.match(self._VALID_URL, url) | |
1220 | if mobj is None: | |
1221 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1222 | return | |
1223 | ||
df372a65 | 1224 | # At this point we have a new video |
9bf7fa52 | 1225 | self._downloader.increment_downloads() |
49c0028a | 1226 | video_id = mobj.group(1) |
1227 | ||
1228 | video_extension = 'mp4' | |
1229 | ||
1230 | # Retrieve video webpage to extract further information | |
490fd7ae | 1231 | request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) |
49c0028a | 1232 | try: |
1233 | self.report_download_webpage(video_id) | |
1234 | webpage = urllib2.urlopen(request).read() | |
1235 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1236 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1237 | return | |
1238 | ||
1239 | # Extract URL, uploader, and title from webpage | |
1240 | self.report_extraction(video_id) | |
490fd7ae RG |
1241 | mobj = re.search(r"download_url:'([^']+)'", webpage) |
1242 | if mobj is None: | |
1243 | video_extension = 'flv' | |
1244 | mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) | |
49c0028a | 1245 | if mobj is None: |
1246 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1247 | return | |
1248 | mediaURL = urllib.unquote(mobj.group(1)) | |
1249 | mediaURL = mediaURL.replace('\\x3d', '\x3d') | |
1250 | mediaURL = mediaURL.replace('\\x26', '\x26') | |
1251 | ||
1252 | video_url = mediaURL | |
1253 | ||
1254 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1255 | if mobj is None: | |
1256 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1257 | return | |
1258 | video_title = mobj.group(1).decode('utf-8') | |
490fd7ae | 1259 | video_title = sanitize_title(video_title) |
31cbdaaf | 1260 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
49c0028a | 1261 | |
7e58d568 RG |
1262 | # Extract video description |
1263 | mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage) | |
1264 | if mobj is None: | |
1265 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
1266 | return | |
1267 | video_description = mobj.group(1).decode('utf-8') | |
1268 | if not video_description: | |
1269 | video_description = 'No description available.' | |
1270 | ||
1271 | # Extract video thumbnail | |
1272 | if self._downloader.params.get('forcethumbnail', False): | |
1273 | request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) | |
1274 | try: | |
1275 | webpage = urllib2.urlopen(request).read() | |
1276 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1277 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1278 | return | |
1279 | mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage) | |
1280 | if mobj is None: | |
1281 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
1282 | return | |
1283 | video_thumbnail = mobj.group(1) | |
1284 | else: # we need something to pass to process_info | |
1285 | video_thumbnail = '' | |
1286 | ||
1287 | ||
49c0028a | 1288 | try: |
1289 | # Process video information | |
1290 | self._downloader.process_info({ | |
1291 | 'id': video_id.decode('utf-8'), | |
1292 | 'url': video_url.decode('utf-8'), | |
6ba562b0 | 1293 | 'uploader': u'NA', |
490fd7ae | 1294 | 'title': video_title, |
31cbdaaf | 1295 | 'stitle': simple_title, |
49c0028a | 1296 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 1297 | 'format': u'NA', |
e616ec0c | 1298 | 'player_url': None, |
49c0028a | 1299 | }) |
73f4e7af RG |
1300 | except UnavailableVideoError: |
1301 | self._downloader.trouble(u'ERROR: unable to download video') | |
49c0028a | 1302 | |
1303 | ||
1304 | class PhotobucketIE(InfoExtractor): | |
1305 | """Information extractor for photobucket.com.""" | |
1306 | ||
1307 | _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)' | |
1308 | ||
1309 | def __init__(self, downloader=None): | |
1310 | InfoExtractor.__init__(self, downloader) | |
1311 | ||
1312 | @staticmethod | |
1313 | def suitable(url): | |
1314 | return (re.match(PhotobucketIE._VALID_URL, url) is not None) | |
1315 | ||
1316 | def report_download_webpage(self, video_id): | |
1317 | """Report webpage download.""" | |
331ce0a0 | 1318 | self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) |
49c0028a | 1319 | |
1320 | def report_extraction(self, video_id): | |
1321 | """Report information extraction.""" | |
331ce0a0 | 1322 | self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) |
49c0028a | 1323 | |
1324 | def _real_initialize(self): | |
1325 | return | |
1326 | ||
1327 | def _real_extract(self, url): | |
1328 | # Extract id from URL | |
1329 | mobj = re.match(self._VALID_URL, url) | |
1330 | if mobj is None: | |
1331 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1332 | return | |
1333 | ||
df372a65 | 1334 | # At this point we have a new video |
9bf7fa52 | 1335 | self._downloader.increment_downloads() |
49c0028a | 1336 | video_id = mobj.group(1) |
1337 | ||
1338 | video_extension = 'flv' | |
1339 | ||
1340 | # Retrieve video webpage to extract further information | |
1341 | request = urllib2.Request(url) | |
1342 | try: | |
1343 | self.report_download_webpage(video_id) | |
1344 | webpage = urllib2.urlopen(request).read() | |
1345 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1346 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1347 | return | |
1348 | ||
1349 | # Extract URL, uploader, and title from webpage | |
1350 | self.report_extraction(video_id) | |
1351 | mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage) | |
1352 | if mobj is None: | |
1353 | self._downloader.trouble(u'ERROR: unable to extract media URL') | |
1354 | return | |
1355 | mediaURL = urllib.unquote(mobj.group(1)) | |
1356 | ||
1357 | video_url = mediaURL | |
1358 | ||
1359 | mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage) | |
1360 | if mobj is None: | |
1361 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1362 | return | |
1363 | video_title = mobj.group(1).decode('utf-8') | |
490fd7ae | 1364 | video_title = sanitize_title(video_title) |
31cbdaaf | 1365 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
49c0028a | 1366 | |
1367 | video_uploader = mobj.group(2).decode('utf-8') | |
1368 | ||
1369 | try: | |
1370 | # Process video information | |
1371 | self._downloader.process_info({ | |
1372 | 'id': video_id.decode('utf-8'), | |
1373 | 'url': video_url.decode('utf-8'), | |
490fd7ae RG |
1374 | 'uploader': video_uploader, |
1375 | 'title': video_title, | |
31cbdaaf | 1376 | 'stitle': simple_title, |
490fd7ae | 1377 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 1378 | 'format': u'NA', |
e616ec0c | 1379 | 'player_url': None, |
490fd7ae | 1380 | }) |
73f4e7af RG |
1381 | except UnavailableVideoError: |
1382 | self._downloader.trouble(u'ERROR: unable to download video') | |
490fd7ae RG |
1383 | |
1384 | ||
61945318 RG |
1385 | class YahooIE(InfoExtractor): |
1386 | """Information extractor for video.yahoo.com.""" | |
1387 | ||
1388 | # _VALID_URL matches all Yahoo! Video URLs | |
1389 | # _VPAGE_URL matches only the extractable '/watch/' URLs | |
1390 | _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' | |
1391 | _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' | |
1392 | ||
1393 | def __init__(self, downloader=None): | |
1394 | InfoExtractor.__init__(self, downloader) | |
1395 | ||
1396 | @staticmethod | |
1397 | def suitable(url): | |
1398 | return (re.match(YahooIE._VALID_URL, url) is not None) | |
1399 | ||
1400 | def report_download_webpage(self, video_id): | |
1401 | """Report webpage download.""" | |
331ce0a0 | 1402 | self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id) |
61945318 RG |
1403 | |
1404 | def report_extraction(self, video_id): | |
1405 | """Report information extraction.""" | |
331ce0a0 | 1406 | self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) |
61945318 RG |
1407 | |
1408 | def _real_initialize(self): | |
1409 | return | |
1410 | ||
df372a65 | 1411 | def _real_extract(self, url, new_video=True): |
61945318 RG |
1412 | # Extract ID from URL |
1413 | mobj = re.match(self._VALID_URL, url) | |
1414 | if mobj is None: | |
1415 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1416 | return | |
1417 | ||
df372a65 | 1418 | # At this point we have a new video |
9bf7fa52 | 1419 | self._downloader.increment_downloads() |
61945318 RG |
1420 | video_id = mobj.group(2) |
1421 | video_extension = 'flv' | |
1422 | ||
1423 | # Rewrite valid but non-extractable URLs as | |
1424 | # extractable English language /watch/ URLs | |
1425 | if re.match(self._VPAGE_URL, url) is None: | |
1426 | request = urllib2.Request(url) | |
1427 | try: | |
1428 | webpage = urllib2.urlopen(request).read() | |
1429 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1430 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1431 | return | |
1432 | ||
1433 | mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) | |
1434 | if mobj is None: | |
1435 | self._downloader.trouble(u'ERROR: Unable to extract id field') | |
1436 | return | |
1437 | yahoo_id = mobj.group(1) | |
1438 | ||
1439 | mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) | |
1440 | if mobj is None: | |
1441 | self._downloader.trouble(u'ERROR: Unable to extract vid field') | |
1442 | return | |
1443 | yahoo_vid = mobj.group(1) | |
1444 | ||
1445 | url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) | |
df372a65 | 1446 | return self._real_extract(url, new_video=False) |
61945318 RG |
1447 | |
1448 | # Retrieve video webpage to extract further information | |
1449 | request = urllib2.Request(url) | |
1450 | try: | |
1451 | self.report_download_webpage(video_id) | |
1452 | webpage = urllib2.urlopen(request).read() | |
1453 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1454 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1455 | return | |
1456 | ||
1457 | # Extract uploader and title from webpage | |
1458 | self.report_extraction(video_id) | |
1459 | mobj = re.search(r'<meta name="title" content="(.*)" />', webpage) | |
1460 | if mobj is None: | |
1461 | self._downloader.trouble(u'ERROR: unable to extract video title') | |
1462 | return | |
1463 | video_title = mobj.group(1).decode('utf-8') | |
1464 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) | |
1465 | ||
1466 | mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage) | |
1467 | if mobj is None: | |
1468 | self._downloader.trouble(u'ERROR: unable to extract video uploader') | |
1469 | return | |
1470 | video_uploader = mobj.group(1).decode('utf-8') | |
1471 | ||
7e58d568 RG |
1472 | # Extract video thumbnail |
1473 | mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage) | |
1474 | if mobj is None: | |
1475 | self._downloader.trouble(u'ERROR: unable to extract video thumbnail') | |
1476 | return | |
1477 | video_thumbnail = mobj.group(1).decode('utf-8') | |
1478 | ||
1479 | # Extract video description | |
1480 | mobj = re.search(r'<meta name="description" content="(.*)" />', webpage) | |
1481 | if mobj is None: | |
1482 | self._downloader.trouble(u'ERROR: unable to extract video description') | |
1483 | return | |
1484 | video_description = mobj.group(1).decode('utf-8') | |
1485 | if not video_description: video_description = 'No description available.' | |
1486 | ||
61945318 RG |
1487 | # Extract video height and width |
1488 | mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage) | |
1489 | if mobj is None: | |
1490 | self._downloader.trouble(u'ERROR: unable to extract video height') | |
1491 | return | |
1492 | yv_video_height = mobj.group(1) | |
1493 | ||
1494 | mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage) | |
1495 | if mobj is None: | |
1496 | self._downloader.trouble(u'ERROR: unable to extract video width') | |
1497 | return | |
1498 | yv_video_width = mobj.group(1) | |
1499 | ||
1500 | # Retrieve video playlist to extract media URL | |
1501 | # I'm not completely sure what all these options are, but we | |
1502 | # seem to need most of them, otherwise the server sends a 401. | |
1503 | yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents | |
1504 | yv_bitrate = '700' # according to Wikipedia this is hard-coded | |
1505 | request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + | |
1506 | '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + | |
1507 | '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') | |
1508 | try: | |
1509 | self.report_download_webpage(video_id) | |
1510 | webpage = urllib2.urlopen(request).read() | |
1511 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1512 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1513 | return | |
1514 | ||
1515 | # Extract media URL from playlist XML | |
1516 | mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage) | |
1517 | if mobj is None: | |
1518 | self._downloader.trouble(u'ERROR: Unable to extract media URL') | |
1519 | return | |
1520 | video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') | |
1521 | video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) | |
1522 | ||
1523 | try: | |
1524 | # Process video information | |
1525 | self._downloader.process_info({ | |
1526 | 'id': video_id.decode('utf-8'), | |
1527 | 'url': video_url, | |
1528 | 'uploader': video_uploader, | |
1529 | 'title': video_title, | |
1530 | 'stitle': simple_title, | |
1531 | 'ext': video_extension.decode('utf-8'), | |
7e58d568 RG |
1532 | 'thumbnail': video_thumbnail.decode('utf-8'), |
1533 | 'description': video_description, | |
1534 | 'thumbnail': video_thumbnail, | |
1535 | 'description': video_description, | |
e616ec0c | 1536 | 'player_url': None, |
61945318 | 1537 | }) |
73f4e7af RG |
1538 | except UnavailableVideoError: |
1539 | self._downloader.trouble(u'ERROR: unable to download video') | |
61945318 RG |
1540 | |
1541 | ||
490fd7ae RG |
1542 | class GenericIE(InfoExtractor): |
1543 | """Generic last-resort information extractor.""" | |
1544 | ||
1545 | def __init__(self, downloader=None): | |
1546 | InfoExtractor.__init__(self, downloader) | |
1547 | ||
1548 | @staticmethod | |
1549 | def suitable(url): | |
1550 | return True | |
1551 | ||
1552 | def report_download_webpage(self, video_id): | |
1553 | """Report webpage download.""" | |
331ce0a0 RG |
1554 | self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') |
1555 | self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) | |
490fd7ae RG |
1556 | |
1557 | def report_extraction(self, video_id): | |
1558 | """Report information extraction.""" | |
331ce0a0 | 1559 | self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) |
490fd7ae RG |
1560 | |
1561 | def _real_initialize(self): | |
1562 | return | |
1563 | ||
1564 | def _real_extract(self, url): | |
df372a65 | 1565 | # At this point we have a new video |
9bf7fa52 | 1566 | self._downloader.increment_downloads() |
df372a65 | 1567 | |
490fd7ae RG |
1568 | video_id = url.split('/')[-1] |
1569 | request = urllib2.Request(url) | |
1570 | try: | |
1571 | self.report_download_webpage(video_id) | |
1572 | webpage = urllib2.urlopen(request).read() | |
1573 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1574 | self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) | |
1575 | return | |
1576 | except ValueError, err: | |
1577 | # since this is the last-resort InfoExtractor, if | |
1578 | # this error is thrown, it'll be thrown here | |
1579 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1580 | return | |
1581 | ||
1582 | # Start with something easy: JW Player in SWFObject | |
1583 | mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) | |
1584 | if mobj is None: | |
1585 | # Broaden the search a little bit | |
1586 | mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) | |
1587 | if mobj is None: | |
1588 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1589 | return | |
1590 | ||
1591 | # It's possible that one of the regexes | |
1592 | # matched, but returned an empty group: | |
1593 | if mobj.group(1) is None: | |
1594 | self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) | |
1595 | return | |
1596 | ||
1597 | video_url = urllib.unquote(mobj.group(1)) | |
1598 | video_id = os.path.basename(video_url) | |
1599 | ||
1600 | # here's a fun little line of code for you: | |
1601 | video_extension = os.path.splitext(video_id)[1][1:] | |
1602 | video_id = os.path.splitext(video_id)[0] | |
1603 | ||
1604 | # it's tempting to parse this further, but you would | |
1605 | # have to take into account all the variations like | |
1606 | # Video Title - Site Name | |
1607 | # Site Name | Video Title | |
1608 | # Video Title - Tagline | Site Name | |
1609 | # and so on and so forth; it's just not practical | |
1610 | mobj = re.search(r'<title>(.*)</title>', webpage) | |
1611 | if mobj is None: | |
1612 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1613 | return | |
1614 | video_title = mobj.group(1).decode('utf-8') | |
1615 | video_title = sanitize_title(video_title) | |
31cbdaaf | 1616 | simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) |
490fd7ae RG |
1617 | |
1618 | # video uploader is domain name | |
1619 | mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) | |
1620 | if mobj is None: | |
1621 | self._downloader.trouble(u'ERROR: unable to extract title') | |
1622 | return | |
1623 | video_uploader = mobj.group(1).decode('utf-8') | |
1624 | ||
1625 | try: | |
1626 | # Process video information | |
1627 | self._downloader.process_info({ | |
1628 | 'id': video_id.decode('utf-8'), | |
1629 | 'url': video_url.decode('utf-8'), | |
1630 | 'uploader': video_uploader, | |
1631 | 'title': video_title, | |
31cbdaaf | 1632 | 'stitle': simple_title, |
49c0028a | 1633 | 'ext': video_extension.decode('utf-8'), |
6ba562b0 | 1634 | 'format': u'NA', |
e616ec0c | 1635 | 'player_url': None, |
49c0028a | 1636 | }) |
73f4e7af RG |
1637 | except UnavailableVideoError, err: |
1638 | self._downloader.trouble(u'ERROR: unable to download video') | |
49c0028a | 1639 | |
1640 | ||
25af2bce RG |
1641 | class YoutubeSearchIE(InfoExtractor): |
1642 | """Information Extractor for YouTube search queries.""" | |
1643 | _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+' | |
1644 | _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en' | |
1645 | _VIDEO_INDICATOR = r'href="/watch\?v=.+?"' | |
304a4d85 | 1646 | _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' |
25af2bce | 1647 | _youtube_ie = None |
fd9288c3 | 1648 | _max_youtube_results = 1000 |
25af2bce | 1649 | |
f995f712 | 1650 | def __init__(self, youtube_ie, downloader=None): |
25af2bce RG |
1651 | InfoExtractor.__init__(self, downloader) |
1652 | self._youtube_ie = youtube_ie | |
1653 | ||
1654 | @staticmethod | |
1655 | def suitable(url): | |
1656 | return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None) | |
1657 | ||
1658 | def report_download_page(self, query, pagenum): | |
1659 | """Report attempt to download playlist page with given number.""" | |
490fd7ae | 1660 | query = query.decode(preferredencoding()) |
331ce0a0 | 1661 | self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) |
25af2bce RG |
1662 | |
1663 | def _real_initialize(self): | |
1664 | self._youtube_ie.initialize() | |
1665 | ||
1666 | def _real_extract(self, query): | |
1667 | mobj = re.match(self._VALID_QUERY, query) | |
1668 | if mobj is None: | |
147753eb | 1669 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) |
6f21f686 | 1670 | return |
25af2bce RG |
1671 | |
1672 | prefix, query = query.split(':') | |
1673 | prefix = prefix[8:] | |
490fd7ae | 1674 | query = query.encode('utf-8') |
f995f712 | 1675 | if prefix == '': |
6f21f686 RG |
1676 | self._download_n_results(query, 1) |
1677 | return | |
f995f712 | 1678 | elif prefix == 'all': |
6f21f686 RG |
1679 | self._download_n_results(query, self._max_youtube_results) |
1680 | return | |
f995f712 | 1681 | else: |
25af2bce | 1682 | try: |
e1f18b8a | 1683 | n = long(prefix) |
25af2bce | 1684 | if n <= 0: |
147753eb | 1685 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) |
6f21f686 | 1686 | return |
257453b9 | 1687 | elif n > self._max_youtube_results: |
6f21f686 | 1688 | self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) |
257453b9 | 1689 | n = self._max_youtube_results |
6f21f686 RG |
1690 | self._download_n_results(query, n) |
1691 | return | |
e1f18b8a | 1692 | except ValueError: # parsing prefix as integer fails |
6f21f686 RG |
1693 | self._download_n_results(query, 1) |
1694 | return | |
25af2bce RG |
1695 | |
1696 | def _download_n_results(self, query, n): | |
1697 | """Downloads a specified number of results for a query""" | |
1698 | ||
1699 | video_ids = [] | |
1700 | already_seen = set() | |
1701 | pagenum = 1 | |
1702 | ||
1703 | while True: | |
1704 | self.report_download_page(query, pagenum) | |
a9633f14 | 1705 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) |
25af2bce RG |
1706 | request = urllib2.Request(result_url, None, std_headers) |
1707 | try: | |
1708 | page = urllib2.urlopen(request).read() | |
1709 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1710 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) |
6f21f686 | 1711 | return |
25af2bce RG |
1712 | |
1713 | # Extract video identifiers | |
1714 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1715 | video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1] | |
1716 | if video_id not in already_seen: | |
1717 | video_ids.append(video_id) | |
1718 | already_seen.add(video_id) | |
1719 | if len(video_ids) == n: | |
1720 | # Specified n videos reached | |
25af2bce | 1721 | for id in video_ids: |
6f21f686 RG |
1722 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
1723 | return | |
25af2bce | 1724 | |
304a4d85 | 1725 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: |
25af2bce | 1726 | for id in video_ids: |
6f21f686 RG |
1727 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
1728 | return | |
25af2bce RG |
1729 | |
1730 | pagenum = pagenum + 1 | |
1731 | ||
7e58d568 RG |
1732 | class GoogleSearchIE(InfoExtractor): |
1733 | """Information Extractor for Google Video search queries.""" | |
1734 | _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' | |
1735 | _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' | |
1736 | _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&' | |
1737 | _MORE_PAGES_INDICATOR = r'<span>Next</span>' | |
1738 | _google_ie = None | |
1739 | _max_google_results = 1000 | |
1740 | ||
1741 | def __init__(self, google_ie, downloader=None): | |
1742 | InfoExtractor.__init__(self, downloader) | |
1743 | self._google_ie = google_ie | |
1744 | ||
1745 | @staticmethod | |
1746 | def suitable(url): | |
1747 | return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None) | |
1748 | ||
1749 | def report_download_page(self, query, pagenum): | |
1750 | """Report attempt to download playlist page with given number.""" | |
1751 | query = query.decode(preferredencoding()) | |
331ce0a0 | 1752 | self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) |
7e58d568 RG |
1753 | |
1754 | def _real_initialize(self): | |
1755 | self._google_ie.initialize() | |
1756 | ||
1757 | def _real_extract(self, query): | |
1758 | mobj = re.match(self._VALID_QUERY, query) | |
1759 | if mobj is None: | |
1760 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
1761 | return | |
1762 | ||
1763 | prefix, query = query.split(':') | |
1764 | prefix = prefix[8:] | |
1765 | query = query.encode('utf-8') | |
1766 | if prefix == '': | |
1767 | self._download_n_results(query, 1) | |
1768 | return | |
1769 | elif prefix == 'all': | |
1770 | self._download_n_results(query, self._max_google_results) | |
1771 | return | |
1772 | else: | |
1773 | try: | |
1774 | n = long(prefix) | |
1775 | if n <= 0: | |
1776 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
1777 | return | |
1778 | elif n > self._max_google_results: | |
1779 | self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) | |
1780 | n = self._max_google_results | |
1781 | self._download_n_results(query, n) | |
1782 | return | |
1783 | except ValueError: # parsing prefix as integer fails | |
1784 | self._download_n_results(query, 1) | |
1785 | return | |
1786 | ||
1787 | def _download_n_results(self, query, n): | |
1788 | """Downloads a specified number of results for a query""" | |
1789 | ||
1790 | video_ids = [] | |
1791 | already_seen = set() | |
1792 | pagenum = 1 | |
1793 | ||
1794 | while True: | |
1795 | self.report_download_page(query, pagenum) | |
1796 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) | |
1797 | request = urllib2.Request(result_url, None, std_headers) | |
1798 | try: | |
1799 | page = urllib2.urlopen(request).read() | |
1800 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1801 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
1802 | return | |
1803 | ||
1804 | # Extract video identifiers | |
1805 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1806 | video_id = mobj.group(1) | |
1807 | if video_id not in already_seen: | |
1808 | video_ids.append(video_id) | |
1809 | already_seen.add(video_id) | |
1810 | if len(video_ids) == n: | |
1811 | # Specified n videos reached | |
1812 | for id in video_ids: | |
1813 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
1814 | return | |
1815 | ||
1816 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1817 | for id in video_ids: | |
1818 | self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) | |
1819 | return | |
1820 | ||
1821 | pagenum = pagenum + 1 | |
1822 | ||
1823 | class YahooSearchIE(InfoExtractor): | |
1824 | """Information Extractor for Yahoo! Video search queries.""" | |
1825 | _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' | |
1826 | _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' | |
1827 | _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' | |
1828 | _MORE_PAGES_INDICATOR = r'\s*Next' | |
1829 | _yahoo_ie = None | |
1830 | _max_yahoo_results = 1000 | |
1831 | ||
1832 | def __init__(self, yahoo_ie, downloader=None): | |
1833 | InfoExtractor.__init__(self, downloader) | |
1834 | self._yahoo_ie = yahoo_ie | |
1835 | ||
1836 | @staticmethod | |
1837 | def suitable(url): | |
1838 | return (re.match(YahooSearchIE._VALID_QUERY, url) is not None) | |
1839 | ||
1840 | def report_download_page(self, query, pagenum): | |
1841 | """Report attempt to download playlist page with given number.""" | |
1842 | query = query.decode(preferredencoding()) | |
331ce0a0 | 1843 | self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) |
7e58d568 RG |
1844 | |
1845 | def _real_initialize(self): | |
1846 | self._yahoo_ie.initialize() | |
1847 | ||
1848 | def _real_extract(self, query): | |
1849 | mobj = re.match(self._VALID_QUERY, query) | |
1850 | if mobj is None: | |
1851 | self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) | |
1852 | return | |
1853 | ||
1854 | prefix, query = query.split(':') | |
1855 | prefix = prefix[8:] | |
1856 | query = query.encode('utf-8') | |
1857 | if prefix == '': | |
1858 | self._download_n_results(query, 1) | |
1859 | return | |
1860 | elif prefix == 'all': | |
1861 | self._download_n_results(query, self._max_yahoo_results) | |
1862 | return | |
1863 | else: | |
1864 | try: | |
1865 | n = long(prefix) | |
1866 | if n <= 0: | |
1867 | self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) | |
1868 | return | |
1869 | elif n > self._max_yahoo_results: | |
1870 | self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) | |
1871 | n = self._max_yahoo_results | |
1872 | self._download_n_results(query, n) | |
1873 | return | |
1874 | except ValueError: # parsing prefix as integer fails | |
1875 | self._download_n_results(query, 1) | |
1876 | return | |
1877 | ||
1878 | def _download_n_results(self, query, n): | |
1879 | """Downloads a specified number of results for a query""" | |
1880 | ||
1881 | video_ids = [] | |
1882 | already_seen = set() | |
1883 | pagenum = 1 | |
1884 | ||
1885 | while True: | |
1886 | self.report_download_page(query, pagenum) | |
1887 | result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum) | |
1888 | request = urllib2.Request(result_url, None, std_headers) | |
1889 | try: | |
1890 | page = urllib2.urlopen(request).read() | |
1891 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
1892 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
1893 | return | |
1894 | ||
1895 | # Extract video identifiers | |
1896 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
1897 | video_id = mobj.group(1) | |
1898 | if video_id not in already_seen: | |
1899 | video_ids.append(video_id) | |
1900 | already_seen.add(video_id) | |
1901 | if len(video_ids) == n: | |
1902 | # Specified n videos reached | |
1903 | for id in video_ids: | |
1904 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
1905 | return | |
1906 | ||
1907 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: | |
1908 | for id in video_ids: | |
1909 | self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) | |
1910 | return | |
1911 | ||
1912 | pagenum = pagenum + 1 | |
1913 | ||
0c2dc87d RG |
1914 | class YoutubePlaylistIE(InfoExtractor): |
1915 | """Information Extractor for YouTube playlists.""" | |
1916 | ||
9177ce4d | 1917 | _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*' |
72ac78b8 | 1918 | _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en' |
0c2dc87d | 1919 | _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' |
ce5cafea | 1920 | _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>' |
0c2dc87d RG |
1921 | _youtube_ie = None |
1922 | ||
1923 | def __init__(self, youtube_ie, downloader=None): | |
1924 | InfoExtractor.__init__(self, downloader) | |
1925 | self._youtube_ie = youtube_ie | |
1926 | ||
1927 | @staticmethod | |
1928 | def suitable(url): | |
1929 | return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None) | |
1930 | ||
1931 | def report_download_page(self, playlist_id, pagenum): | |
1932 | """Report attempt to download playlist page with given number.""" | |
331ce0a0 | 1933 | self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) |
0c2dc87d RG |
1934 | |
1935 | def _real_initialize(self): | |
1936 | self._youtube_ie.initialize() | |
1937 | ||
1938 | def _real_extract(self, url): | |
1939 | # Extract playlist id | |
1940 | mobj = re.match(self._VALID_URL, url) | |
1941 | if mobj is None: | |
147753eb | 1942 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) |
6f21f686 | 1943 | return |
0c2dc87d RG |
1944 | |
1945 | # Download playlist pages | |
1946 | playlist_id = mobj.group(1) | |
1947 | video_ids = [] | |
1948 | pagenum = 1 | |
1949 | ||
1950 | while True: | |
1951 | self.report_download_page(playlist_id, pagenum) | |
1952 | request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers) | |
1953 | try: | |
1954 | page = urllib2.urlopen(request).read() | |
1955 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
147753eb | 1956 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) |
6f21f686 | 1957 | return |
0c2dc87d RG |
1958 | |
1959 | # Extract video identifiers | |
27d98b6e | 1960 | ids_in_page = [] |
0c2dc87d | 1961 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): |
27d98b6e RG |
1962 | if mobj.group(1) not in ids_in_page: |
1963 | ids_in_page.append(mobj.group(1)) | |
1964 | video_ids.extend(ids_in_page) | |
0c2dc87d | 1965 | |
ce5cafea | 1966 | if re.search(self._MORE_PAGES_INDICATOR, page) is None: |
0c2dc87d RG |
1967 | break |
1968 | pagenum = pagenum + 1 | |
1969 | ||
8cc44341 RG |
1970 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
1971 | playlistend = self._downloader.params.get('playlistend', -1) | |
1972 | video_ids = video_ids[playliststart:playlistend] | |
1973 | ||
0c2dc87d | 1974 | for id in video_ids: |
6f21f686 RG |
1975 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) |
1976 | return | |
0c2dc87d | 1977 | |
c39c05cd A |
1978 | class YoutubeUserIE(InfoExtractor): |
1979 | """Information Extractor for YouTube users.""" | |
1980 | ||
1981 | _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)' | |
1982 | _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s' | |
75a4cf3c | 1983 | _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this. |
c39c05cd A |
1984 | _youtube_ie = None |
1985 | ||
1986 | def __init__(self, youtube_ie, downloader=None): | |
1987 | InfoExtractor.__init__(self, downloader) | |
1988 | self._youtube_ie = youtube_ie | |
1989 | ||
1990 | @staticmethod | |
1991 | def suitable(url): | |
1992 | return (re.match(YoutubeUserIE._VALID_URL, url) is not None) | |
1993 | ||
1994 | def report_download_page(self, username): | |
1995 | """Report attempt to download user page.""" | |
331ce0a0 | 1996 | self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username)) |
c39c05cd A |
1997 | |
1998 | def _real_initialize(self): | |
1999 | self._youtube_ie.initialize() | |
2000 | ||
2001 | def _real_extract(self, url): | |
2002 | # Extract username | |
2003 | mobj = re.match(self._VALID_URL, url) | |
2004 | if mobj is None: | |
2005 | self._downloader.trouble(u'ERROR: invalid url: %s' % url) | |
2006 | return | |
2007 | ||
2008 | # Download user page | |
2009 | username = mobj.group(1) | |
2010 | video_ids = [] | |
2011 | pagenum = 1 | |
2012 | ||
2013 | self.report_download_page(username) | |
2014 | request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers) | |
2015 | try: | |
2016 | page = urllib2.urlopen(request).read() | |
2017 | except (urllib2.URLError, httplib.HTTPException, socket.error), err: | |
2018 | self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) | |
2019 | return | |
2020 | ||
2021 | # Extract video identifiers | |
2022 | ids_in_page = [] | |
2023 | ||
2024 | for mobj in re.finditer(self._VIDEO_INDICATOR, page): | |
c39c05cd A |
2025 | if mobj.group(1) not in ids_in_page: |
2026 | ids_in_page.append(mobj.group(1)) | |
2027 | video_ids.extend(ids_in_page) | |
2028 | ||
8cc44341 RG |
2029 | playliststart = self._downloader.params.get('playliststart', 1) - 1 |
2030 | playlistend = self._downloader.params.get('playlistend', -1) | |
2031 | video_ids = video_ids[playliststart:playlistend] | |
204c9398 | 2032 | |
c39c05cd A |
2033 | for id in video_ids: |
2034 | self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) | |
2035 | return | |
2036 | ||
65cd34c5 RG |
2037 | class PostProcessor(object): |
2038 | """Post Processor class. | |
2039 | ||
2040 | PostProcessor objects can be added to downloaders with their | |
2041 | add_post_processor() method. When the downloader has finished a | |
2042 | successful download, it will take its internal chain of PostProcessors | |
2043 | and start calling the run() method on each one of them, first with | |
2044 | an initial argument and then with the returned value of the previous | |
2045 | PostProcessor. | |
2046 | ||
2047 | The chain will be stopped if one of them ever returns None or the end | |
2048 | of the chain is reached. | |
2049 | ||
2050 | PostProcessor objects follow a "mutual registration" process similar | |
2051 | to InfoExtractor objects. | |
2052 | """ | |
2053 | ||
2054 | _downloader = None | |
2055 | ||
2056 | def __init__(self, downloader=None): | |
2057 | self._downloader = downloader | |
2058 | ||
65cd34c5 RG |
2059 | def set_downloader(self, downloader): |
2060 | """Sets the downloader for this PP.""" | |
2061 | self._downloader = downloader | |
2062 | ||
2063 | def run(self, information): | |
2064 | """Run the PostProcessor. | |
2065 | ||
2066 | The "information" argument is a dictionary like the ones | |
2f11508a | 2067 | composed by InfoExtractors. The only difference is that this |
65cd34c5 RG |
2068 | one has an extra field called "filepath" that points to the |
2069 | downloaded file. | |
2070 | ||
2071 | When this method returns None, the postprocessing chain is | |
2072 | stopped. However, this method may return an information | |
2073 | dictionary that will be passed to the next postprocessing | |
2074 | object in the chain. It can be the one it received after | |
2075 | changing some fields. | |
2076 | ||
2077 | In addition, this method may raise a PostProcessingError | |
2078 | exception that will be taken into account by the downloader | |
2079 | it was called from. | |
2080 | """ | |
2081 | return information # by default, do nothing | |
2082 | ||
2083 | ### MAIN PROGRAM ### | |
4fa74b52 RG |
2084 | if __name__ == '__main__': |
2085 | try: | |
f9f1e798 | 2086 | # Modules needed only when running the main program |
209e9e27 | 2087 | import getpass |
f9f1e798 RG |
2088 | import optparse |
2089 | ||
4bec29ef RG |
2090 | # Function to update the program file with the latest version from bitbucket.org |
2091 | def update_self(downloader, filename): | |
2092 | # Note: downloader only used for options | |
2093 | if not os.access (filename, os.W_OK): | |
2094 | sys.exit('ERROR: no write permissions on %s' % filename) | |
2095 | ||
331ce0a0 | 2096 | downloader.to_screen('Updating to latest stable version...') |
893a13df | 2097 | latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' |
4bec29ef | 2098 | latest_version = urllib.urlopen(latest_url).read().strip() |
893a13df | 2099 | prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version |
4bec29ef RG |
2100 | newcontent = urllib.urlopen(prog_url).read() |
2101 | stream = open(filename, 'w') | |
2102 | stream.write(newcontent) | |
2103 | stream.close() | |
331ce0a0 | 2104 | downloader.to_screen('Updated to version %s' % latest_version) |
4bec29ef | 2105 | |
f9f1e798 | 2106 | # Parse command line |
209e9e27 | 2107 | parser = optparse.OptionParser( |
7b7759f5 | 2108 | usage='Usage: %prog [options] url...', |
c34e3584 | 2109 | version='2010.10.24', |
7b7759f5 | 2110 | conflict_handler='resolve', |
2111 | ) | |
2112 | ||
209e9e27 RG |
2113 | parser.add_option('-h', '--help', |
2114 | action='help', help='print this help text and exit') | |
2115 | parser.add_option('-v', '--version', | |
2116 | action='version', help='print program version and exit') | |
4bec29ef RG |
2117 | parser.add_option('-U', '--update', |
2118 | action='store_true', dest='update_self', help='update this program to latest stable version') | |
7b7759f5 | 2119 | parser.add_option('-i', '--ignore-errors', |
2120 | action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) | |
2121 | parser.add_option('-r', '--rate-limit', | |
2b06c33d | 2122 | dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') |
7031008c | 2123 | parser.add_option('-R', '--retries', |
2b06c33d | 2124 | dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) |
204c9398 RG |
2125 | parser.add_option('--playlist-start', |
2126 | dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) | |
8cc44341 RG |
2127 | parser.add_option('--playlist-end', |
2128 | dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) | |
7b7759f5 | 2129 | |
2130 | authentication = optparse.OptionGroup(parser, 'Authentication Options') | |
2131 | authentication.add_option('-u', '--username', | |
2b06c33d | 2132 | dest='username', metavar='USERNAME', help='account username') |
7b7759f5 | 2133 | authentication.add_option('-p', '--password', |
2b06c33d | 2134 | dest='password', metavar='PASSWORD', help='account password') |
7b7759f5 | 2135 | authentication.add_option('-n', '--netrc', |
209e9e27 | 2136 | action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) |
7b7759f5 | 2137 | parser.add_option_group(authentication) |
2138 | ||
2139 | video_format = optparse.OptionGroup(parser, 'Video Format Options') | |
2140 | video_format.add_option('-f', '--format', | |
2b06c33d | 2141 | action='store', dest='format', metavar='FORMAT', help='video format code') |
7b7759f5 | 2142 | video_format.add_option('-m', '--mobile-version', |
b74c859d | 2143 | action='store_const', dest='format', help='alias for -f 17', const='17') |
6ba562b0 RG |
2144 | video_format.add_option('--all-formats', |
2145 | action='store_const', dest='format', help='download all available video formats', const='-1') | |
f2413e67 | 2146 | video_format.add_option('--max-quality', |
460d8acb | 2147 | action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') |
2962317d RG |
2148 | video_format.add_option('-b', '--best-quality', |
2149 | action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)') | |
7b7759f5 | 2150 | parser.add_option_group(video_format) |
2151 | ||
2152 | verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') | |
2153 | verbosity.add_option('-q', '--quiet', | |
2154 | action='store_true', dest='quiet', help='activates quiet mode', default=False) | |
2155 | verbosity.add_option('-s', '--simulate', | |
2156 | action='store_true', dest='simulate', help='do not download video', default=False) | |
2157 | verbosity.add_option('-g', '--get-url', | |
2158 | action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) | |
2159 | verbosity.add_option('-e', '--get-title', | |
2160 | action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) | |
7e58d568 RG |
2161 | verbosity.add_option('--get-thumbnail', |
2162 | action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False) | |
2163 | verbosity.add_option('--get-description', | |
2164 | action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) | |
d9835247 RG |
2165 | verbosity.add_option('--no-progress', |
2166 | action='store_true', dest='noprogress', help='do not print progress bar', default=False) | |
7b7759f5 | 2167 | parser.add_option_group(verbosity) |
2168 | ||
2169 | filesystem = optparse.OptionGroup(parser, 'Filesystem Options') | |
1c76e23e RG |
2170 | filesystem.add_option('-t', '--title', |
2171 | action='store_true', dest='usetitle', help='use title in file name', default=False) | |
2172 | filesystem.add_option('-l', '--literal', | |
2173 | action='store_true', dest='useliteral', help='use literal title in file name', default=False) | |
1e47d226 NA |
2174 | filesystem.add_option('-A', '--auto-number', |
2175 | action='store_true', dest='autonumber', help='number downloaded URLs starting from 00000', default=False) | |
7b7759f5 | 2176 | filesystem.add_option('-o', '--output', |
2b06c33d | 2177 | dest='outtmpl', metavar='TEMPLATE', help='output filename template') |
7b7759f5 | 2178 | filesystem.add_option('-a', '--batch-file', |
2b06c33d | 2179 | dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') |
7b7759f5 | 2180 | filesystem.add_option('-w', '--no-overwrites', |
0beeff4b | 2181 | action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) |
f76c2df6 PI |
2182 | filesystem.add_option('-c', '--continue', |
2183 | action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) | |
80066952 RG |
2184 | filesystem.add_option('--cookies', |
2185 | dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') | |
7b7759f5 | 2186 | parser.add_option_group(filesystem) |
2187 | ||
209e9e27 | 2188 | (opts, args) = parser.parse_args() |
2a7353b8 | 2189 | |
80066952 RG |
2190 | # Open appropriate CookieJar |
2191 | if opts.cookiefile is None: | |
2192 | jar = cookielib.CookieJar() | |
2193 | else: | |
2194 | try: | |
2195 | jar = cookielib.MozillaCookieJar(opts.cookiefile) | |
e0c982c8 RG |
2196 | if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): |
2197 | jar.load() | |
80066952 RG |
2198 | except (IOError, OSError), err: |
2199 | sys.exit(u'ERROR: unable to open cookie file') | |
2200 | ||
2201 | # General configuration | |
2202 | cookie_processor = urllib2.HTTPCookieProcessor(jar) | |
2203 | urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) | |
2204 | urllib2.install_opener(urllib2.build_opener(cookie_processor)) | |
2205 | socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) | |
2206 | ||
c6fd0bb8 | 2207 | # Batch file verification |
d1580ed9 | 2208 | batchurls = [] |
c6fd0bb8 RG |
2209 | if opts.batchfile is not None: |
2210 | try: | |
2a7353b8 RG |
2211 | if opts.batchfile == '-': |
2212 | batchfd = sys.stdin | |
2213 | else: | |
2214 | batchfd = open(opts.batchfile, 'r') | |
2215 | batchurls = batchfd.readlines() | |
b65740e4 | 2216 | batchurls = [x.strip() for x in batchurls] |
817e8f52 | 2217 | batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] |
c6fd0bb8 RG |
2218 | except IOError: |
2219 | sys.exit(u'ERROR: batch file could not be read') | |
2220 | all_urls = batchurls + args | |
2221 | ||
209e9e27 | 2222 | # Conflicting, missing and erroneous options |
2962317d RG |
2223 | if opts.bestquality: |
2224 | print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n' | |
209e9e27 | 2225 | if opts.usenetrc and (opts.username is not None or opts.password is not None): |
2740c509 | 2226 | parser.error(u'using .netrc conflicts with giving username/password') |
209e9e27 | 2227 | if opts.password is not None and opts.username is None: |
2740c509 | 2228 | parser.error(u'account username missing') |
1e47d226 NA |
2229 | if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): |
2230 | parser.error(u'using output template conflicts with using title, literal title or auto number') | |
209e9e27 | 2231 | if opts.usetitle and opts.useliteral: |
2740c509 | 2232 | parser.error(u'using title conflicts with using literal title') |
209e9e27 | 2233 | if opts.username is not None and opts.password is None: |
76a7f364 | 2234 | opts.password = getpass.getpass(u'Type account password and press return:') |
acd3d842 RG |
2235 | if opts.ratelimit is not None: |
2236 | numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) | |
2237 | if numeric_limit is None: | |
2740c509 | 2238 | parser.error(u'invalid rate limit specified') |
acd3d842 | 2239 | opts.ratelimit = numeric_limit |
7031008c RG |
2240 | if opts.retries is not None: |
2241 | try: | |
2242 | opts.retries = long(opts.retries) | |
2243 | except (TypeError, ValueError), err: | |
2244 | parser.error(u'invalid retry count specified') | |
8cc44341 RG |
2245 | try: |
2246 | opts.playliststart = long(opts.playliststart) | |
2247 | if opts.playliststart <= 0: | |
2248 | raise ValueError | |
2249 | except (TypeError, ValueError), err: | |
2250 | parser.error(u'invalid playlist start number specified') | |
2251 | try: | |
2252 | opts.playlistend = long(opts.playlistend) | |
2253 | if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): | |
2254 | raise ValueError | |
2255 | except (TypeError, ValueError), err: | |
2256 | parser.error(u'invalid playlist end number specified') | |
4fa74b52 RG |
2257 | |
2258 | # Information extractors | |
2259 | youtube_ie = YoutubeIE() | |
020f7150 | 2260 | metacafe_ie = MetacafeIE(youtube_ie) |
4135fa45 | 2261 | dailymotion_ie = DailymotionIE() |
0c2dc87d | 2262 | youtube_pl_ie = YoutubePlaylistIE(youtube_ie) |
c39c05cd | 2263 | youtube_user_ie = YoutubeUserIE(youtube_ie) |
25af2bce | 2264 | youtube_search_ie = YoutubeSearchIE(youtube_ie) |
49c0028a | 2265 | google_ie = GoogleIE() |
7e58d568 | 2266 | google_search_ie = GoogleSearchIE(google_ie) |
49c0028a | 2267 | photobucket_ie = PhotobucketIE() |
61945318 | 2268 | yahoo_ie = YahooIE() |
7e58d568 | 2269 | yahoo_search_ie = YahooSearchIE(yahoo_ie) |
490fd7ae | 2270 | generic_ie = GenericIE() |
4fa74b52 RG |
2271 | |
2272 | # File downloader | |
9fcd8355 | 2273 | fd = FileDownloader({ |
209e9e27 RG |
2274 | 'usenetrc': opts.usenetrc, |
2275 | 'username': opts.username, | |
2276 | 'password': opts.password, | |
7e58d568 | 2277 | 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), |
209e9e27 RG |
2278 | 'forceurl': opts.geturl, |
2279 | 'forcetitle': opts.gettitle, | |
7e58d568 RG |
2280 | 'forcethumbnail': opts.getthumbnail, |
2281 | 'forcedescription': opts.getdescription, | |
2282 | 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), | |
320becd6 | 2283 | 'format': opts.format, |
f2413e67 | 2284 | 'format_limit': opts.format_limit, |
eae2666c | 2285 | 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) |
6ba562b0 RG |
2286 | or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') |
2287 | or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') | |
2288 | or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') | |
1e47d226 NA |
2289 | or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') |
2290 | or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') | |
76a7f364 RG |
2291 | or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') |
2292 | or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') | |
1e47d226 | 2293 | or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') |
76a7f364 | 2294 | or u'%(id)s.%(ext)s'), |
0086d1ec | 2295 | 'ignoreerrors': opts.ignoreerrors, |
acd3d842 | 2296 | 'ratelimit': opts.ratelimit, |
0beeff4b | 2297 | 'nooverwrites': opts.nooverwrites, |
7031008c | 2298 | 'retries': opts.retries, |
7db85b2c | 2299 | 'continuedl': opts.continue_dl, |
d9835247 | 2300 | 'noprogress': opts.noprogress, |
204c9398 | 2301 | 'playliststart': opts.playliststart, |
8cc44341 | 2302 | 'playlistend': opts.playlistend, |
331ce0a0 | 2303 | 'logtostderr': opts.outtmpl == '-', |
9fcd8355 | 2304 | }) |
25af2bce | 2305 | fd.add_info_extractor(youtube_search_ie) |
0c2dc87d | 2306 | fd.add_info_extractor(youtube_pl_ie) |
c39c05cd | 2307 | fd.add_info_extractor(youtube_user_ie) |
020f7150 | 2308 | fd.add_info_extractor(metacafe_ie) |
4135fa45 | 2309 | fd.add_info_extractor(dailymotion_ie) |
4fa74b52 | 2310 | fd.add_info_extractor(youtube_ie) |
49c0028a | 2311 | fd.add_info_extractor(google_ie) |
7e58d568 | 2312 | fd.add_info_extractor(google_search_ie) |
49c0028a | 2313 | fd.add_info_extractor(photobucket_ie) |
61945318 | 2314 | fd.add_info_extractor(yahoo_ie) |
7e58d568 | 2315 | fd.add_info_extractor(yahoo_search_ie) |
4bec29ef | 2316 | |
490fd7ae RG |
2317 | # This must come last since it's the |
2318 | # fallback if none of the others work | |
2319 | fd.add_info_extractor(generic_ie) | |
2320 | ||
4bec29ef RG |
2321 | # Update version |
2322 | if opts.update_self: | |
2323 | update_self(fd, sys.argv[0]) | |
2324 | ||
2325 | # Maybe do nothing | |
2326 | if len(all_urls) < 1: | |
2327 | if not opts.update_self: | |
2328 | parser.error(u'you must provide at least one URL') | |
2329 | else: | |
2330 | sys.exit() | |
c6fd0bb8 | 2331 | retcode = fd.download(all_urls) |
80066952 RG |
2332 | |
2333 | # Dump cookie jar if requested | |
2334 | if opts.cookiefile is not None: | |
2335 | try: | |
2336 | jar.save() | |
2337 | except (IOError, OSError), err: | |
2338 | sys.exit(u'ERROR: unable to save cookie jar') | |
2339 | ||
bb681b88 | 2340 | sys.exit(retcode) |
4fa74b52 | 2341 | |
e5bf0f55 RG |
2342 | except DownloadError: |
2343 | sys.exit(1) | |
2344 | except SameFileError: | |
76a7f364 | 2345 | sys.exit(u'ERROR: fixed output name but more than one file to download') |
4fa74b52 | 2346 | except KeyboardInterrupt: |
76a7f364 | 2347 | sys.exit(u'\nERROR: Interrupted by user') |