]>
Commit | Line | Data |
---|---|---|
8222d8de JMF |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | ||
6febd1c1 | 4 | from __future__ import absolute_import, unicode_literals |
8222d8de | 5 | |
26e63931 | 6 | import collections |
9d2ecdbc | 7 | import datetime |
c1c9a79c | 8 | import errno |
8222d8de | 9 | import io |
8694c600 | 10 | import json |
62fec3b2 | 11 | import locale |
8222d8de | 12 | import os |
dca08720 | 13 | import platform |
8222d8de JMF |
14 | import re |
15 | import shutil | |
dca08720 | 16 | import subprocess |
8222d8de JMF |
17 | import socket |
18 | import sys | |
19 | import time | |
20 | import traceback | |
21 | ||
1e5b9a95 PH |
22 | if os.name == 'nt': |
23 | import ctypes | |
24 | ||
ce02ed60 | 25 | from .utils import ( |
dca08720 | 26 | compat_cookiejar, |
ce02ed60 | 27 | compat_http_client, |
ce02ed60 PH |
28 | compat_str, |
29 | compat_urllib_error, | |
30 | compat_urllib_request, | |
31 | ContentTooShortError, | |
32 | date_from_str, | |
33 | DateRange, | |
acd69589 | 34 | DEFAULT_OUTTMPL, |
ce02ed60 PH |
35 | determine_ext, |
36 | DownloadError, | |
37 | encodeFilename, | |
38 | ExtractorError, | |
02dbf93f | 39 | format_bytes, |
525ef922 | 40 | formatSeconds, |
1c088fa8 | 41 | get_term_width, |
ce02ed60 | 42 | locked_file, |
dca08720 | 43 | make_HTTPS_handler, |
ce02ed60 | 44 | MaxDownloadsReached, |
b7ab0590 | 45 | PagedList, |
ce02ed60 | 46 | PostProcessingError, |
dca08720 | 47 | platform_name, |
ce02ed60 PH |
48 | preferredencoding, |
49 | SameFileError, | |
50 | sanitize_filename, | |
51 | subtitles_filename, | |
52 | takewhile_inclusive, | |
53 | UnavailableVideoError, | |
29eb5174 | 54 | url_basename, |
ce02ed60 PH |
55 | write_json_file, |
56 | write_string, | |
dca08720 | 57 | YoutubeDLHandler, |
6350728b | 58 | prepend_extension, |
ce02ed60 | 59 | ) |
023fa8c4 | 60 | from .extractor import get_info_extractor, gen_extractors |
3bc2ddcc | 61 | from .downloader import get_suitable_downloader |
56327689 | 62 | from .postprocessor import FFmpegMergerPP |
dca08720 | 63 | from .version import __version__ |
8222d8de JMF |
64 | |
65 | ||
66 | class YoutubeDL(object): | |
67 | """YoutubeDL class. | |
68 | ||
69 | YoutubeDL objects are the ones responsible of downloading the | |
70 | actual video file and writing it to disk if the user has requested | |
71 | it, among some other tasks. In most cases there should be one per | |
72 | program. As, given a video URL, the downloader doesn't know how to | |
73 | extract all the needed information, task that InfoExtractors do, it | |
74 | has to pass the URL to one of them. | |
75 | ||
76 | For this, YoutubeDL objects have a method that allows | |
77 | InfoExtractors to be registered in a given order. When it is passed | |
78 | a URL, the YoutubeDL object handles it to the first InfoExtractor it | |
79 | finds that reports being able to handle it. The InfoExtractor extracts | |
80 | all the information about the video or videos the URL refers to, and | |
81 | YoutubeDL process the extracted information, possibly using a File | |
82 | Downloader to download the video. | |
83 | ||
84 | YoutubeDL objects accept a lot of parameters. In order not to saturate | |
85 | the object constructor with arguments, it receives a dictionary of | |
86 | options instead. These options are available through the params | |
87 | attribute for the InfoExtractors to use. The YoutubeDL also | |
88 | registers itself as the downloader in charge for the InfoExtractors | |
89 | that are added to it, so this is a "mutual registration". | |
90 | ||
91 | Available options: | |
92 | ||
93 | username: Username for authentication purposes. | |
94 | password: Password for authentication purposes. | |
c6c19746 | 95 | videopassword: Password for acces a video. |
8222d8de JMF |
96 | usenetrc: Use netrc for authentication instead. |
97 | verbose: Print additional info to stdout. | |
98 | quiet: Do not print messages to stdout. | |
ad8915b7 | 99 | no_warnings: Do not print out anything for warnings. |
8222d8de JMF |
100 | forceurl: Force printing final URL. |
101 | forcetitle: Force printing title. | |
102 | forceid: Force printing ID. | |
103 | forcethumbnail: Force printing thumbnail URL. | |
104 | forcedescription: Force printing description. | |
105 | forcefilename: Force printing final filename. | |
525ef922 | 106 | forceduration: Force printing duration. |
8694c600 | 107 | forcejson: Force printing info_dict as JSON. |
8222d8de JMF |
108 | simulate: Do not download the video files. |
109 | format: Video format code. | |
110 | format_limit: Highest quality format to try. | |
111 | outtmpl: Template for output names. | |
112 | restrictfilenames: Do not allow "&" and spaces in file names | |
113 | ignoreerrors: Do not stop on download errors. | |
114 | nooverwrites: Prevent overwriting files. | |
115 | playliststart: Playlist item to start at. | |
116 | playlistend: Playlist item to end at. | |
117 | matchtitle: Download only matching titles. | |
118 | rejecttitle: Reject downloads for matching titles. | |
8bf9319e | 119 | logger: Log messages to a logging.Logger instance. |
8222d8de JMF |
120 | logtostderr: Log messages to stderr instead of stdout. |
121 | writedescription: Write the video description to a .description file | |
122 | writeinfojson: Write the video description to a .info.json file | |
1fb07d10 | 123 | writeannotations: Write the video annotations to a .annotations.xml file |
8222d8de JMF |
124 | writethumbnail: Write the thumbnail image to a file |
125 | writesubtitles: Write the video subtitles to a file | |
b004821f | 126 | writeautomaticsub: Write the automatic subtitles to a file |
8222d8de | 127 | allsubtitles: Downloads all the subtitles of the video |
0b7f3118 | 128 | (requires writesubtitles or writeautomaticsub) |
8222d8de | 129 | listsubtitles: Lists all available subtitles for the video |
b98a6b2f | 130 | subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt) |
aa6a10c4 | 131 | subtitleslangs: List of languages of the subtitles to download |
8222d8de JMF |
132 | keepvideo: Keep the video file after post-processing |
133 | daterange: A DateRange object, download only if the upload_date is in the range. | |
134 | skip_download: Skip the actual download of the video file | |
c35f9e72 | 135 | cachedir: Location of the cache files in the filesystem. |
c3c88a26 | 136 | None to disable filesystem cache. |
47192f92 | 137 | noplaylist: Download single video instead of a playlist if in doubt. |
8dbe9899 PH |
138 | age_limit: An integer representing the user's age in years. |
139 | Unsuitable videos for the given age are skipped. | |
5fe18bdb PH |
140 | min_views: An integer representing the minimum view count the video |
141 | must have in order to not be skipped. | |
142 | Videos without view count information are always | |
143 | downloaded. None for no limit. | |
144 | max_views: An integer representing the maximum view count. | |
145 | Videos that are more popular than that are not | |
146 | downloaded. | |
147 | Videos without view count information are always | |
148 | downloaded. None for no limit. | |
149 | download_archive: File name of a file where all downloads are recorded. | |
c1c9a79c PH |
150 | Videos already present in the file are not downloaded |
151 | again. | |
dca08720 | 152 | cookiefile: File name where cookies should be read from and dumped to. |
a1ee09e8 | 153 | nocheckcertificate:Do not verify SSL certificates |
7e8c0af0 PH |
154 | prefer_insecure: Use HTTP instead of HTTPS to retrieve information. |
155 | At the moment, this is only supported by YouTube. | |
a1ee09e8 | 156 | proxy: URL of the proxy server to use |
e344693b | 157 | socket_timeout: Time to wait for unresponsive hosts, in seconds |
0783b09b PH |
158 | bidi_workaround: Work around buggy terminals without bidirectional text |
159 | support, using fridibi | |
a0ddb8a2 | 160 | debug_printtraffic:Print out sent and received HTTP traffic |
7b0817e8 | 161 | include_ads: Download ads as well |
04b4d394 PH |
162 | default_search: Prepend this string if an input url is not valid. |
163 | 'auto' for elaborate guessing | |
62fec3b2 | 164 | encoding: Use this encoding instead of the system-specified. |
e8ee972c | 165 | extract_flat: Do not resolve URLs, return the immediate result. |
fe7e0c98 | 166 | |
8222d8de JMF |
167 | The following parameters are not used by YoutubeDL itself, they are used by |
168 | the FileDownloader: | |
169 | nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, | |
170 | noresizebuffer, retries, continuedl, noprogress, consoletitle | |
76b1bd67 JMF |
171 | |
172 | The following options are used by the post processors: | |
173 | prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, | |
174 | otherwise prefer avconv. | |
8d31fa3c | 175 | exec_cmd: Arbitrary command to run after downloading |
8222d8de JMF |
176 | """ |
177 | ||
178 | params = None | |
179 | _ies = [] | |
180 | _pps = [] | |
181 | _download_retcode = None | |
182 | _num_downloads = None | |
183 | _screen_file = None | |
184 | ||
a3fb4675 | 185 | def __init__(self, params=None): |
8222d8de | 186 | """Create a FileDownloader object with the given options.""" |
e9f9a10f JMF |
187 | if params is None: |
188 | params = {} | |
8222d8de | 189 | self._ies = [] |
56c73665 | 190 | self._ies_instances = {} |
8222d8de | 191 | self._pps = [] |
933605d7 | 192 | self._progress_hooks = [] |
8222d8de JMF |
193 | self._download_retcode = 0 |
194 | self._num_downloads = 0 | |
195 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] | |
0783b09b | 196 | self._err_file = sys.stderr |
e9f9a10f | 197 | self.params = params |
34308b30 | 198 | |
0783b09b | 199 | if params.get('bidi_workaround', False): |
1c088fa8 PH |
200 | try: |
201 | import pty | |
202 | master, slave = pty.openpty() | |
203 | width = get_term_width() | |
204 | if width is None: | |
205 | width_args = [] | |
206 | else: | |
207 | width_args = ['-w', str(width)] | |
5d681e96 | 208 | sp_kwargs = dict( |
1c088fa8 PH |
209 | stdin=subprocess.PIPE, |
210 | stdout=slave, | |
211 | stderr=self._err_file) | |
5d681e96 PH |
212 | try: |
213 | self._output_process = subprocess.Popen( | |
214 | ['bidiv'] + width_args, **sp_kwargs | |
215 | ) | |
216 | except OSError: | |
5d681e96 PH |
217 | self._output_process = subprocess.Popen( |
218 | ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) | |
219 | self._output_channel = os.fdopen(master, 'rb') | |
1c088fa8 PH |
220 | except OSError as ose: |
221 | if ose.errno == 2: | |
6febd1c1 | 222 | self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.') |
1c088fa8 PH |
223 | else: |
224 | raise | |
0783b09b | 225 | |
34308b30 PH |
226 | if (sys.version_info >= (3,) and sys.platform != 'win32' and |
227 | sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] | |
228 | and not params['restrictfilenames']): | |
229 | # On Python 3, the Unicode filesystem API will throw errors (#1474) | |
230 | self.report_warning( | |
6febd1c1 PH |
231 | 'Assuming --restrict-filenames since file system encoding ' |
232 | 'cannot encode all charactes. ' | |
233 | 'Set the LC_ALL environment variable to fix this.') | |
4a98cdbf | 234 | self.params['restrictfilenames'] = True |
34308b30 | 235 | |
a3927cf7 | 236 | if '%(stitle)s' in self.params.get('outtmpl', ''): |
6febd1c1 | 237 | self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') |
8222d8de | 238 | |
dca08720 PH |
239 | self._setup_opener() |
240 | ||
8222d8de JMF |
241 | def add_info_extractor(self, ie): |
242 | """Add an InfoExtractor object to the end of the list.""" | |
243 | self._ies.append(ie) | |
56c73665 | 244 | self._ies_instances[ie.ie_key()] = ie |
8222d8de JMF |
245 | ie.set_downloader(self) |
246 | ||
56c73665 JMF |
247 | def get_info_extractor(self, ie_key): |
248 | """ | |
249 | Get an instance of an IE with name ie_key, it will try to get one from | |
250 | the _ies list, if there's no instance it will create a new one and add | |
251 | it to the extractor list. | |
252 | """ | |
253 | ie = self._ies_instances.get(ie_key) | |
254 | if ie is None: | |
255 | ie = get_info_extractor(ie_key)() | |
256 | self.add_info_extractor(ie) | |
257 | return ie | |
258 | ||
023fa8c4 JMF |
259 | def add_default_info_extractors(self): |
260 | """ | |
261 | Add the InfoExtractors returned by gen_extractors to the end of the list | |
262 | """ | |
263 | for ie in gen_extractors(): | |
264 | self.add_info_extractor(ie) | |
265 | ||
8222d8de JMF |
266 | def add_post_processor(self, pp): |
267 | """Add a PostProcessor object to the end of the chain.""" | |
268 | self._pps.append(pp) | |
269 | pp.set_downloader(self) | |
270 | ||
933605d7 JMF |
271 | def add_progress_hook(self, ph): |
272 | """Add the progress hook (currently only for the file downloader)""" | |
273 | self._progress_hooks.append(ph) | |
8ab470f1 | 274 | |
1c088fa8 | 275 | def _bidi_workaround(self, message): |
5d681e96 | 276 | if not hasattr(self, '_output_channel'): |
1c088fa8 PH |
277 | return message |
278 | ||
5d681e96 | 279 | assert hasattr(self, '_output_process') |
11b85ce6 | 280 | assert isinstance(message, compat_str) |
6febd1c1 PH |
281 | line_count = message.count('\n') + 1 |
282 | self._output_process.stdin.write((message + '\n').encode('utf-8')) | |
5d681e96 | 283 | self._output_process.stdin.flush() |
6febd1c1 | 284 | res = ''.join(self._output_channel.readline().decode('utf-8') |
1c088fa8 | 285 | for _ in range(line_count)) |
6febd1c1 | 286 | return res[:-len('\n')] |
1c088fa8 | 287 | |
8222d8de | 288 | def to_screen(self, message, skip_eol=False): |
0783b09b PH |
289 | """Print message to stdout if not in quiet mode.""" |
290 | return self.to_stdout(message, skip_eol, check_quiet=True) | |
291 | ||
734f90bb | 292 | def _write_string(self, s, out=None): |
b58ddb32 | 293 | write_string(s, out=out, encoding=self.params.get('encoding')) |
734f90bb | 294 | |
0783b09b | 295 | def to_stdout(self, message, skip_eol=False, check_quiet=False): |
8222d8de | 296 | """Print message to stdout if not in quiet mode.""" |
8bf9319e | 297 | if self.params.get('logger'): |
43afe285 | 298 | self.params['logger'].debug(message) |
0783b09b | 299 | elif not check_quiet or not self.params.get('quiet', False): |
1c088fa8 | 300 | message = self._bidi_workaround(message) |
6febd1c1 | 301 | terminator = ['\n', ''][skip_eol] |
8222d8de | 302 | output = message + terminator |
1c088fa8 | 303 | |
734f90bb | 304 | self._write_string(output, self._screen_file) |
8222d8de JMF |
305 | |
306 | def to_stderr(self, message): | |
307 | """Print message to stderr.""" | |
11b85ce6 | 308 | assert isinstance(message, compat_str) |
8bf9319e | 309 | if self.params.get('logger'): |
43afe285 IB |
310 | self.params['logger'].error(message) |
311 | else: | |
1c088fa8 | 312 | message = self._bidi_workaround(message) |
6febd1c1 | 313 | output = message + '\n' |
734f90bb | 314 | self._write_string(output, self._err_file) |
8222d8de | 315 | |
1e5b9a95 PH |
316 | def to_console_title(self, message): |
317 | if not self.params.get('consoletitle', False): | |
318 | return | |
319 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
320 | # c_wchar_p() might not be necessary if `message` is | |
321 | # already of type unicode() | |
322 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
323 | elif 'TERM' in os.environ: | |
734f90bb | 324 | self._write_string('\033]0;%s\007' % message, self._screen_file) |
1e5b9a95 | 325 | |
bdde425c PH |
326 | def save_console_title(self): |
327 | if not self.params.get('consoletitle', False): | |
328 | return | |
329 | if 'TERM' in os.environ: | |
efd6c574 | 330 | # Save the title on stack |
734f90bb | 331 | self._write_string('\033[22;0t', self._screen_file) |
bdde425c PH |
332 | |
333 | def restore_console_title(self): | |
334 | if not self.params.get('consoletitle', False): | |
335 | return | |
336 | if 'TERM' in os.environ: | |
efd6c574 | 337 | # Restore the title from stack |
734f90bb | 338 | self._write_string('\033[23;0t', self._screen_file) |
bdde425c PH |
339 | |
340 | def __enter__(self): | |
341 | self.save_console_title() | |
342 | return self | |
343 | ||
344 | def __exit__(self, *args): | |
345 | self.restore_console_title() | |
f89197d7 | 346 | |
dca08720 PH |
347 | if self.params.get('cookiefile') is not None: |
348 | self.cookiejar.save() | |
bdde425c | 349 | |
8222d8de JMF |
350 | def trouble(self, message=None, tb=None): |
351 | """Determine action to take when a download problem appears. | |
352 | ||
353 | Depending on if the downloader has been configured to ignore | |
354 | download errors or not, this method may throw an exception or | |
355 | not when errors are found, after printing the message. | |
356 | ||
357 | tb, if given, is additional traceback information. | |
358 | """ | |
359 | if message is not None: | |
360 | self.to_stderr(message) | |
361 | if self.params.get('verbose'): | |
362 | if tb is None: | |
363 | if sys.exc_info()[0]: # if .trouble has been called from an except block | |
6febd1c1 | 364 | tb = '' |
8222d8de | 365 | if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: |
6febd1c1 | 366 | tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) |
8222d8de JMF |
367 | tb += compat_str(traceback.format_exc()) |
368 | else: | |
369 | tb_data = traceback.format_list(traceback.extract_stack()) | |
6febd1c1 | 370 | tb = ''.join(tb_data) |
8222d8de JMF |
371 | self.to_stderr(tb) |
372 | if not self.params.get('ignoreerrors', False): | |
373 | if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: | |
374 | exc_info = sys.exc_info()[1].exc_info | |
375 | else: | |
376 | exc_info = sys.exc_info() | |
377 | raise DownloadError(message, exc_info) | |
378 | self._download_retcode = 1 | |
379 | ||
380 | def report_warning(self, message): | |
381 | ''' | |
382 | Print the message to stderr, it will be prefixed with 'WARNING:' | |
383 | If stderr is a tty file the 'WARNING:' will be colored | |
384 | ''' | |
6d07ce01 JMF |
385 | if self.params.get('logger') is not None: |
386 | self.params['logger'].warning(message) | |
8222d8de | 387 | else: |
ad8915b7 PH |
388 | if self.params.get('no_warnings'): |
389 | return | |
6d07ce01 JMF |
390 | if self._err_file.isatty() and os.name != 'nt': |
391 | _msg_header = '\033[0;33mWARNING:\033[0m' | |
392 | else: | |
393 | _msg_header = 'WARNING:' | |
394 | warning_message = '%s %s' % (_msg_header, message) | |
395 | self.to_stderr(warning_message) | |
8222d8de JMF |
396 | |
397 | def report_error(self, message, tb=None): | |
398 | ''' | |
399 | Do the same as trouble, but prefixes the message with 'ERROR:', colored | |
400 | in red if stderr is a tty file. | |
401 | ''' | |
0783b09b | 402 | if self._err_file.isatty() and os.name != 'nt': |
6febd1c1 | 403 | _msg_header = '\033[0;31mERROR:\033[0m' |
8222d8de | 404 | else: |
6febd1c1 PH |
405 | _msg_header = 'ERROR:' |
406 | error_message = '%s %s' % (_msg_header, message) | |
8222d8de JMF |
407 | self.trouble(error_message, tb) |
408 | ||
8222d8de JMF |
409 | def report_file_already_downloaded(self, file_name): |
410 | """Report file has already been fully downloaded.""" | |
411 | try: | |
6febd1c1 | 412 | self.to_screen('[download] %s has already been downloaded' % file_name) |
ce02ed60 | 413 | except UnicodeEncodeError: |
6febd1c1 | 414 | self.to_screen('[download] The file has already been downloaded') |
8222d8de | 415 | |
8222d8de JMF |
416 | def prepare_filename(self, info_dict): |
417 | """Generate the output filename.""" | |
418 | try: | |
419 | template_dict = dict(info_dict) | |
420 | ||
421 | template_dict['epoch'] = int(time.time()) | |
422 | autonumber_size = self.params.get('autonumber_size') | |
423 | if autonumber_size is None: | |
424 | autonumber_size = 5 | |
6febd1c1 | 425 | autonumber_templ = '%0' + str(autonumber_size) + 'd' |
8222d8de | 426 | template_dict['autonumber'] = autonumber_templ % self._num_downloads |
702665c0 | 427 | if template_dict.get('playlist_index') is not None: |
c6b4132a | 428 | template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index']) |
17b75c0d PH |
429 | if template_dict.get('resolution') is None: |
430 | if template_dict.get('width') and template_dict.get('height'): | |
431 | template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height']) | |
432 | elif template_dict.get('height'): | |
805ef3c6 | 433 | template_dict['resolution'] = '%sp' % template_dict['height'] |
17b75c0d | 434 | elif template_dict.get('width'): |
805ef3c6 | 435 | template_dict['resolution'] = '?x%d' % template_dict['width'] |
8222d8de | 436 | |
586a91b6 | 437 | sanitize = lambda k, v: sanitize_filename( |
45598aab | 438 | compat_str(v), |
8222d8de | 439 | restricted=self.params.get('restrictfilenames'), |
6febd1c1 | 440 | is_id=(k == 'id')) |
586a91b6 | 441 | template_dict = dict((k, sanitize(k, v)) |
45598aab PH |
442 | for k, v in template_dict.items() |
443 | if v is not None) | |
6febd1c1 | 444 | template_dict = collections.defaultdict(lambda: 'NA', template_dict) |
8222d8de | 445 | |
acd69589 PH |
446 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
447 | tmpl = os.path.expanduser(outtmpl) | |
586a91b6 | 448 | filename = tmpl % template_dict |
8222d8de | 449 | return filename |
8222d8de | 450 | except ValueError as err: |
6febd1c1 | 451 | self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') |
8222d8de JMF |
452 | return None |
453 | ||
454 | def _match_entry(self, info_dict): | |
455 | """ Returns None iff the file should be downloaded """ | |
456 | ||
6febd1c1 | 457 | video_title = info_dict.get('title', info_dict.get('id', 'video')) |
7012b23c PH |
458 | if 'title' in info_dict: |
459 | # This can happen when we're just evaluating the playlist | |
460 | title = info_dict['title'] | |
461 | matchtitle = self.params.get('matchtitle', False) | |
462 | if matchtitle: | |
463 | if not re.search(matchtitle, title, re.IGNORECASE): | |
6febd1c1 | 464 | return '"' + title + '" title did not match pattern "' + matchtitle + '"' |
7012b23c PH |
465 | rejecttitle = self.params.get('rejecttitle', False) |
466 | if rejecttitle: | |
467 | if re.search(rejecttitle, title, re.IGNORECASE): | |
6febd1c1 | 468 | return '"' + title + '" title matched reject pattern "' + rejecttitle + '"' |
8222d8de JMF |
469 | date = info_dict.get('upload_date', None) |
470 | if date is not None: | |
471 | dateRange = self.params.get('daterange', DateRange()) | |
472 | if date not in dateRange: | |
6febd1c1 | 473 | return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) |
5fe18bdb PH |
474 | view_count = info_dict.get('view_count', None) |
475 | if view_count is not None: | |
476 | min_views = self.params.get('min_views') | |
477 | if min_views is not None and view_count < min_views: | |
6febd1c1 | 478 | return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views) |
5fe18bdb PH |
479 | max_views = self.params.get('max_views') |
480 | if max_views is not None and view_count > max_views: | |
6febd1c1 | 481 | return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) |
8dbe9899 PH |
482 | age_limit = self.params.get('age_limit') |
483 | if age_limit is not None: | |
be843678 PH |
484 | actual_age_limit = info_dict.get('age_limit') |
485 | if actual_age_limit is None: | |
486 | actual_age_limit = 0 | |
487 | if age_limit < actual_age_limit: | |
6febd1c1 | 488 | return 'Skipping "' + title + '" because it is age restricted' |
c1c9a79c | 489 | if self.in_download_archive(info_dict): |
6febd1c1 | 490 | return '%s has already been recorded in archive' % video_title |
8222d8de | 491 | return None |
fe7e0c98 | 492 | |
b6c45014 JMF |
493 | @staticmethod |
494 | def add_extra_info(info_dict, extra_info): | |
495 | '''Set the keys from extra_info in info dict if they are missing''' | |
496 | for key, value in extra_info.items(): | |
497 | info_dict.setdefault(key, value) | |
498 | ||
7fc3fa05 PH |
499 | def extract_info(self, url, download=True, ie_key=None, extra_info={}, |
500 | process=True): | |
8222d8de JMF |
501 | ''' |
502 | Returns a list with a dictionary for each video we find. | |
503 | If 'download', also downloads the videos. | |
504 | extra_info is a dict containing the extra values to add to each result | |
505 | ''' | |
fe7e0c98 | 506 | |
8222d8de | 507 | if ie_key: |
56c73665 | 508 | ies = [self.get_info_extractor(ie_key)] |
8222d8de JMF |
509 | else: |
510 | ies = self._ies | |
511 | ||
512 | for ie in ies: | |
513 | if not ie.suitable(url): | |
514 | continue | |
515 | ||
516 | if not ie.working(): | |
6febd1c1 PH |
517 | self.report_warning('The program functionality for this site has been marked as broken, ' |
518 | 'and will probably not work.') | |
8222d8de JMF |
519 | |
520 | try: | |
521 | ie_result = ie.extract(url) | |
522 | if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) | |
523 | break | |
524 | if isinstance(ie_result, list): | |
525 | # Backwards compatibility: old IE result format | |
8222d8de JMF |
526 | ie_result = { |
527 | '_type': 'compat_list', | |
528 | 'entries': ie_result, | |
529 | } | |
ea38e55f | 530 | self.add_default_extra_info(ie_result, ie, url) |
7fc3fa05 PH |
531 | if process: |
532 | return self.process_ie_result(ie_result, download, extra_info) | |
533 | else: | |
534 | return ie_result | |
8222d8de JMF |
535 | except ExtractorError as de: # An error we somewhat expected |
536 | self.report_error(compat_str(de), de.format_traceback()) | |
537 | break | |
d3e5bbf4 PH |
538 | except MaxDownloadsReached: |
539 | raise | |
8222d8de JMF |
540 | except Exception as e: |
541 | if self.params.get('ignoreerrors', False): | |
542 | self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) | |
543 | break | |
544 | else: | |
545 | raise | |
546 | else: | |
1a489545 | 547 | self.report_error('no suitable InfoExtractor for URL %s' % url) |
fe7e0c98 | 548 | |
ea38e55f PH |
549 | def add_default_extra_info(self, ie_result, ie, url): |
550 | self.add_extra_info(ie_result, { | |
551 | 'extractor': ie.IE_NAME, | |
552 | 'webpage_url': url, | |
553 | 'webpage_url_basename': url_basename(url), | |
554 | 'extractor_key': ie.ie_key(), | |
555 | }) | |
556 | ||
8222d8de JMF |
557 | def process_ie_result(self, ie_result, download=True, extra_info={}): |
558 | """ | |
559 | Take the result of the ie(may be modified) and resolve all unresolved | |
560 | references (URLs, playlist items). | |
561 | ||
562 | It will also download the videos if 'download'. | |
563 | Returns the resolved ie_result. | |
564 | """ | |
565 | ||
e8ee972c PH |
566 | result_type = ie_result.get('_type', 'video') |
567 | ||
568 | if self.params.get('extract_flat', False): | |
569 | if result_type in ('url', 'url_transparent'): | |
570 | return ie_result | |
571 | ||
8222d8de | 572 | if result_type == 'video': |
b6c45014 | 573 | self.add_extra_info(ie_result, extra_info) |
feee2ecf | 574 | return self.process_video_result(ie_result, download=download) |
8222d8de JMF |
575 | elif result_type == 'url': |
576 | # We have to add extra_info to the results because it may be | |
577 | # contained in a playlist | |
578 | return self.extract_info(ie_result['url'], | |
579 | download, | |
580 | ie_key=ie_result.get('ie_key'), | |
581 | extra_info=extra_info) | |
7fc3fa05 PH |
582 | elif result_type == 'url_transparent': |
583 | # Use the information from the embedding page | |
584 | info = self.extract_info( | |
585 | ie_result['url'], ie_key=ie_result.get('ie_key'), | |
586 | extra_info=extra_info, download=False, process=False) | |
587 | ||
588 | def make_result(embedded_info): | |
589 | new_result = ie_result.copy() | |
590 | for f in ('_type', 'url', 'ext', 'player_url', 'formats', | |
1538eff6 | 591 | 'entries', 'ie_key', 'duration', |
ef4fd848 PH |
592 | 'subtitles', 'annotations', 'format', |
593 | 'thumbnail', 'thumbnails'): | |
7fc3fa05 PH |
594 | if f in new_result: |
595 | del new_result[f] | |
596 | if f in embedded_info: | |
597 | new_result[f] = embedded_info[f] | |
598 | return new_result | |
599 | new_result = make_result(info) | |
600 | ||
601 | assert new_result.get('_type') != 'url_transparent' | |
602 | if new_result.get('_type') == 'compat_list': | |
603 | new_result['entries'] = [ | |
604 | make_result(e) for e in new_result['entries']] | |
605 | ||
606 | return self.process_ie_result( | |
607 | new_result, download=download, extra_info=extra_info) | |
8222d8de JMF |
608 | elif result_type == 'playlist': |
609 | # We process each entry in the playlist | |
610 | playlist = ie_result.get('title', None) or ie_result.get('id', None) | |
6febd1c1 | 611 | self.to_screen('[download] Downloading playlist: %s' % playlist) |
8222d8de JMF |
612 | |
613 | playlist_results = [] | |
614 | ||
8222d8de | 615 | playliststart = self.params.get('playliststart', 1) - 1 |
a19fd00c PH |
616 | playlistend = self.params.get('playlistend', None) |
617 | # For backwards compatibility, interpret -1 as whole list | |
8222d8de | 618 | if playlistend == -1: |
a19fd00c | 619 | playlistend = None |
8222d8de | 620 | |
b7ab0590 PH |
621 | if isinstance(ie_result['entries'], list): |
622 | n_all_entries = len(ie_result['entries']) | |
623 | entries = ie_result['entries'][playliststart:playlistend] | |
624 | n_entries = len(entries) | |
625 | self.to_screen( | |
626 | "[%s] playlist %s: Collected %d video ids (downloading %d of them)" % | |
627 | (ie_result['extractor'], playlist, n_all_entries, n_entries)) | |
628 | else: | |
629 | assert isinstance(ie_result['entries'], PagedList) | |
630 | entries = ie_result['entries'].getslice( | |
631 | playliststart, playlistend) | |
632 | n_entries = len(entries) | |
633 | self.to_screen( | |
634 | "[%s] playlist %s: Downloading %d videos" % | |
635 | (ie_result['extractor'], playlist, n_entries)) | |
8222d8de | 636 | |
fe7e0c98 | 637 | for i, entry in enumerate(entries, 1): |
6febd1c1 | 638 | self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries)) |
8222d8de | 639 | extra = { |
c6b4132a | 640 | 'n_entries': n_entries, |
fe7e0c98 JMF |
641 | 'playlist': playlist, |
642 | 'playlist_index': i + playliststart, | |
b6c45014 | 643 | 'extractor': ie_result['extractor'], |
9103bbc5 | 644 | 'webpage_url': ie_result['webpage_url'], |
29eb5174 | 645 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 646 | 'extractor_key': ie_result['extractor_key'], |
fe7e0c98 | 647 | } |
7012b23c PH |
648 | |
649 | reason = self._match_entry(entry) | |
650 | if reason is not None: | |
6febd1c1 | 651 | self.to_screen('[download] ' + reason) |
7012b23c PH |
652 | continue |
653 | ||
8222d8de JMF |
654 | entry_result = self.process_ie_result(entry, |
655 | download=download, | |
656 | extra_info=extra) | |
657 | playlist_results.append(entry_result) | |
658 | ie_result['entries'] = playlist_results | |
659 | return ie_result | |
660 | elif result_type == 'compat_list': | |
661 | def _fixup(r): | |
b6c45014 | 662 | self.add_extra_info(r, |
9103bbc5 JMF |
663 | { |
664 | 'extractor': ie_result['extractor'], | |
665 | 'webpage_url': ie_result['webpage_url'], | |
29eb5174 | 666 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 667 | 'extractor_key': ie_result['extractor_key'], |
9103bbc5 | 668 | }) |
8222d8de JMF |
669 | return r |
670 | ie_result['entries'] = [ | |
b6c45014 | 671 | self.process_ie_result(_fixup(r), download, extra_info) |
8222d8de JMF |
672 | for r in ie_result['entries'] |
673 | ] | |
674 | return ie_result | |
675 | else: | |
676 | raise Exception('Invalid result type: %s' % result_type) | |
677 | ||
a9c58ad9 JMF |
678 | def select_format(self, format_spec, available_formats): |
679 | if format_spec == 'best' or format_spec is None: | |
680 | return available_formats[-1] | |
681 | elif format_spec == 'worst': | |
682 | return available_formats[0] | |
ba7678f9 PH |
683 | elif format_spec == 'bestaudio': |
684 | audio_formats = [ | |
685 | f for f in available_formats | |
686 | if f.get('vcodec') == 'none'] | |
687 | if audio_formats: | |
688 | return audio_formats[-1] | |
689 | elif format_spec == 'worstaudio': | |
690 | audio_formats = [ | |
691 | f for f in available_formats | |
692 | if f.get('vcodec') == 'none'] | |
693 | if audio_formats: | |
694 | return audio_formats[0] | |
bc6d5978 JMF |
695 | elif format_spec == 'bestvideo': |
696 | video_formats = [ | |
697 | f for f in available_formats | |
698 | if f.get('acodec') == 'none'] | |
699 | if video_formats: | |
700 | return video_formats[-1] | |
701 | elif format_spec == 'worstvideo': | |
702 | video_formats = [ | |
703 | f for f in available_formats | |
704 | if f.get('acodec') == 'none'] | |
705 | if video_formats: | |
706 | return video_formats[0] | |
a9c58ad9 | 707 | else: |
6febd1c1 | 708 | extensions = ['mp4', 'flv', 'webm', '3gp'] |
49e86983 JMF |
709 | if format_spec in extensions: |
710 | filter_f = lambda f: f['ext'] == format_spec | |
711 | else: | |
712 | filter_f = lambda f: f['format_id'] == format_spec | |
fe7e0c98 | 713 | matches = list(filter(filter_f, available_formats)) |
a9c58ad9 JMF |
714 | if matches: |
715 | return matches[-1] | |
716 | return None | |
717 | ||
dd82ffea JMF |
718 | def process_video_result(self, info_dict, download=True): |
719 | assert info_dict.get('_type', 'video') == 'video' | |
720 | ||
bec1fad2 PH |
721 | if 'id' not in info_dict: |
722 | raise ExtractorError('Missing "id" field in extractor result') | |
723 | if 'title' not in info_dict: | |
724 | raise ExtractorError('Missing "title" field in extractor result') | |
725 | ||
dd82ffea JMF |
726 | if 'playlist' not in info_dict: |
727 | # It isn't part of a playlist | |
728 | info_dict['playlist'] = None | |
729 | info_dict['playlist_index'] = None | |
730 | ||
d5519808 PH |
731 | thumbnails = info_dict.get('thumbnails') |
732 | if thumbnails: | |
be6d7229 PH |
733 | thumbnails.sort(key=lambda t: ( |
734 | t.get('width'), t.get('height'), t.get('url'))) | |
d5519808 PH |
735 | for t in thumbnails: |
736 | if 'width' in t and 'height' in t: | |
737 | t['resolution'] = '%dx%d' % (t['width'], t['height']) | |
738 | ||
739 | if thumbnails and 'thumbnail' not in info_dict: | |
740 | info_dict['thumbnail'] = thumbnails[-1]['url'] | |
741 | ||
c9ae7b95 | 742 | if 'display_id' not in info_dict and 'id' in info_dict: |
0afef30b PH |
743 | info_dict['display_id'] = info_dict['id'] |
744 | ||
955c4514 | 745 | if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None: |
9d2ecdbc | 746 | upload_date = datetime.datetime.utcfromtimestamp( |
955c4514 | 747 | info_dict['timestamp']) |
9d2ecdbc PH |
748 | info_dict['upload_date'] = upload_date.strftime('%Y%m%d') |
749 | ||
6ff000b8 | 750 | # This extractors handle format selection themselves |
6febd1c1 | 751 | if info_dict['extractor'] in ['Youku']: |
12893efe JMF |
752 | if download: |
753 | self.process_info(info_dict) | |
6ff000b8 JMF |
754 | return info_dict |
755 | ||
dd82ffea JMF |
756 | # We now pick which formats have to be downloaded |
757 | if info_dict.get('formats') is None: | |
758 | # There's only one format available | |
759 | formats = [info_dict] | |
760 | else: | |
761 | formats = info_dict['formats'] | |
762 | ||
db95dc13 PH |
763 | if not formats: |
764 | raise ExtractorError('No video formats found!') | |
765 | ||
dd82ffea | 766 | # We check that all the formats have the format and format_id fields |
db95dc13 | 767 | for i, format in enumerate(formats): |
bec1fad2 PH |
768 | if 'url' not in format: |
769 | raise ExtractorError('Missing "url" key in result (index %d)' % i) | |
770 | ||
dd82ffea | 771 | if format.get('format_id') is None: |
8016c922 | 772 | format['format_id'] = compat_str(i) |
8c51aa65 | 773 | if format.get('format') is None: |
6febd1c1 | 774 | format['format'] = '{id} - {res}{note}'.format( |
8c51aa65 JMF |
775 | id=format['format_id'], |
776 | res=self.format_resolution(format), | |
6febd1c1 | 777 | note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', |
8c51aa65 | 778 | ) |
c1002e96 PH |
779 | # Automatically determine file extension if missing |
780 | if 'ext' not in format: | |
cce929ea | 781 | format['ext'] = determine_ext(format['url']).lower() |
dd82ffea | 782 | |
99e206d5 JMF |
783 | format_limit = self.params.get('format_limit', None) |
784 | if format_limit: | |
f4d96df0 PH |
785 | formats = list(takewhile_inclusive( |
786 | lambda f: f['format_id'] != format_limit, formats | |
787 | )) | |
4bcc7bd1 PH |
788 | |
789 | # TODO Central sorting goes here | |
99e206d5 | 790 | |
f89197d7 | 791 | if formats[0] is not info_dict: |
b3d9ef88 JMF |
792 | # only set the 'formats' fields if the original info_dict list them |
793 | # otherwise we end up with a circular reference, the first (and unique) | |
f89197d7 | 794 | # element in the 'formats' field in info_dict is info_dict itself, |
b3d9ef88 JMF |
795 | # wich can't be exported to json |
796 | info_dict['formats'] = formats | |
bfaae0a7 | 797 | if self.params.get('listformats', None): |
798 | self.list_formats(info_dict) | |
799 | return | |
800 | ||
de3ef3ed | 801 | req_format = self.params.get('format') |
a9c58ad9 JMF |
802 | if req_format is None: |
803 | req_format = 'best' | |
dd82ffea | 804 | formats_to_download = [] |
dd82ffea | 805 | # The -1 is for supporting YoutubeIE |
a9c58ad9 | 806 | if req_format in ('-1', 'all'): |
dd82ffea JMF |
807 | formats_to_download = formats |
808 | else: | |
a9c5e5ca | 809 | # We can accept formats requested in the format: 34/5/best, we pick |
416a5efc | 810 | # the first that is available, starting from left |
dd82ffea JMF |
811 | req_formats = req_format.split('/') |
812 | for rf in req_formats: | |
6350728b JMF |
813 | if re.match(r'.+?\+.+?', rf) is not None: |
814 | # Two formats have been requested like '137+139' | |
815 | format_1, format_2 = rf.split('+') | |
816 | formats_info = (self.select_format(format_1, formats), | |
817 | self.select_format(format_2, formats)) | |
818 | if all(formats_info): | |
a9c5e5ca PH |
819 | selected_format = { |
820 | 'requested_formats': formats_info, | |
821 | 'format': rf, | |
822 | 'ext': formats_info[0]['ext'], | |
823 | } | |
6350728b JMF |
824 | else: |
825 | selected_format = None | |
826 | else: | |
827 | selected_format = self.select_format(rf, formats) | |
a9c58ad9 JMF |
828 | if selected_format is not None: |
829 | formats_to_download = [selected_format] | |
dd82ffea JMF |
830 | break |
831 | if not formats_to_download: | |
6febd1c1 | 832 | raise ExtractorError('requested format not available', |
78a3a9f8 | 833 | expected=True) |
dd82ffea JMF |
834 | |
835 | if download: | |
836 | if len(formats_to_download) > 1: | |
6febd1c1 | 837 | self.to_screen('[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) |
dd82ffea JMF |
838 | for format in formats_to_download: |
839 | new_info = dict(info_dict) | |
840 | new_info.update(format) | |
841 | self.process_info(new_info) | |
842 | # We update the info dict with the best quality format (backwards compatibility) | |
843 | info_dict.update(formats_to_download[-1]) | |
844 | return info_dict | |
845 | ||
8222d8de JMF |
846 | def process_info(self, info_dict): |
847 | """Process a single resolved IE result.""" | |
848 | ||
849 | assert info_dict.get('_type', 'video') == 'video' | |
fd288278 PH |
850 | |
851 | max_downloads = self.params.get('max_downloads') | |
852 | if max_downloads is not None: | |
853 | if self._num_downloads >= int(max_downloads): | |
854 | raise MaxDownloadsReached() | |
8222d8de JMF |
855 | |
856 | info_dict['fulltitle'] = info_dict['title'] | |
857 | if len(info_dict['title']) > 200: | |
6febd1c1 | 858 | info_dict['title'] = info_dict['title'][:197] + '...' |
8222d8de JMF |
859 | |
860 | # Keep for backwards compatibility | |
861 | info_dict['stitle'] = info_dict['title'] | |
862 | ||
11b85ce6 | 863 | if 'format' not in info_dict: |
8222d8de JMF |
864 | info_dict['format'] = info_dict['ext'] |
865 | ||
866 | reason = self._match_entry(info_dict) | |
867 | if reason is not None: | |
6febd1c1 | 868 | self.to_screen('[download] ' + reason) |
8222d8de JMF |
869 | return |
870 | ||
fd288278 | 871 | self._num_downloads += 1 |
8222d8de JMF |
872 | |
873 | filename = self.prepare_filename(info_dict) | |
874 | ||
875 | # Forced printings | |
876 | if self.params.get('forcetitle', False): | |
0783b09b | 877 | self.to_stdout(info_dict['fulltitle']) |
8222d8de | 878 | if self.params.get('forceid', False): |
0783b09b | 879 | self.to_stdout(info_dict['id']) |
8222d8de | 880 | if self.params.get('forceurl', False): |
edde6c56 | 881 | # For RTMP URLs, also include the playpath |
6febd1c1 | 882 | self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) |
216d71d0 | 883 | if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: |
0783b09b | 884 | self.to_stdout(info_dict['thumbnail']) |
216d71d0 | 885 | if self.params.get('forcedescription', False) and info_dict.get('description') is not None: |
0783b09b | 886 | self.to_stdout(info_dict['description']) |
8222d8de | 887 | if self.params.get('forcefilename', False) and filename is not None: |
0783b09b | 888 | self.to_stdout(filename) |
525ef922 PH |
889 | if self.params.get('forceduration', False) and info_dict.get('duration') is not None: |
890 | self.to_stdout(formatSeconds(info_dict['duration'])) | |
8222d8de | 891 | if self.params.get('forceformat', False): |
0783b09b | 892 | self.to_stdout(info_dict['format']) |
9d153818 | 893 | if self.params.get('forcejson', False): |
a0d96c98 | 894 | info_dict['_filename'] = filename |
0783b09b | 895 | self.to_stdout(json.dumps(info_dict)) |
8222d8de JMF |
896 | |
897 | # Do nothing else if in simulate mode | |
898 | if self.params.get('simulate', False): | |
899 | return | |
900 | ||
901 | if filename is None: | |
902 | return | |
903 | ||
904 | try: | |
905 | dn = os.path.dirname(encodeFilename(filename)) | |
d26e981d | 906 | if dn and not os.path.exists(dn): |
8222d8de JMF |
907 | os.makedirs(dn) |
908 | except (OSError, IOError) as err: | |
6febd1c1 | 909 | self.report_error('unable to create directory ' + compat_str(err)) |
8222d8de JMF |
910 | return |
911 | ||
912 | if self.params.get('writedescription', False): | |
6febd1c1 | 913 | descfn = filename + '.description' |
7b6fefc9 | 914 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): |
6febd1c1 | 915 | self.to_screen('[info] Video description is already present') |
7b6fefc9 PH |
916 | else: |
917 | try: | |
6febd1c1 | 918 | self.to_screen('[info] Writing video description to: ' + descfn) |
7b6fefc9 PH |
919 | with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: |
920 | descfile.write(info_dict['description']) | |
921 | except (KeyError, TypeError): | |
6febd1c1 | 922 | self.report_warning('There\'s no description to write.') |
7b6fefc9 | 923 | except (OSError, IOError): |
6febd1c1 | 924 | self.report_error('Cannot write description file ' + descfn) |
7b6fefc9 | 925 | return |
8222d8de | 926 | |
1fb07d10 | 927 | if self.params.get('writeannotations', False): |
6febd1c1 | 928 | annofn = filename + '.annotations.xml' |
7b6fefc9 | 929 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): |
6febd1c1 | 930 | self.to_screen('[info] Video annotations are already present') |
7b6fefc9 PH |
931 | else: |
932 | try: | |
6febd1c1 | 933 | self.to_screen('[info] Writing video annotations to: ' + annofn) |
7b6fefc9 PH |
934 | with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: |
935 | annofile.write(info_dict['annotations']) | |
936 | except (KeyError, TypeError): | |
6febd1c1 | 937 | self.report_warning('There are no annotations to write.') |
7b6fefc9 | 938 | except (OSError, IOError): |
6febd1c1 | 939 | self.report_error('Cannot write annotations file: ' + annofn) |
7b6fefc9 | 940 | return |
1fb07d10 | 941 | |
c4a91be7 | 942 | subtitles_are_requested = any([self.params.get('writesubtitles', False), |
0b7f3118 | 943 | self.params.get('writeautomaticsub')]) |
c4a91be7 | 944 | |
fe7e0c98 | 945 | if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']: |
8222d8de JMF |
946 | # subtitles download errors are already managed as troubles in relevant IE |
947 | # that way it will silently go on when used with unsupporting IE | |
8222d8de | 948 | subtitles = info_dict['subtitles'] |
ca715127 | 949 | sub_format = self.params.get('subtitlesformat', 'srt') |
5d51a883 JMF |
950 | for sub_lang in subtitles.keys(): |
951 | sub = subtitles[sub_lang] | |
6804038d JMF |
952 | if sub is None: |
953 | continue | |
8222d8de | 954 | try: |
d4051a8e | 955 | sub_filename = subtitles_filename(filename, sub_lang, sub_format) |
7b6fefc9 | 956 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): |
6febd1c1 | 957 | self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) |
7b6fefc9 | 958 | else: |
6febd1c1 | 959 | self.to_screen('[info] Writing video subtitles to: ' + sub_filename) |
7b6fefc9 PH |
960 | with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: |
961 | subfile.write(sub) | |
8222d8de | 962 | except (OSError, IOError): |
e4db1951 | 963 | self.report_error('Cannot write subtitles file ' + sub_filename) |
8222d8de JMF |
964 | return |
965 | ||
8222d8de | 966 | if self.params.get('writeinfojson', False): |
6febd1c1 | 967 | infofn = os.path.splitext(filename)[0] + '.info.json' |
7b6fefc9 | 968 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)): |
6febd1c1 | 969 | self.to_screen('[info] Video description metadata is already present') |
7b6fefc9 | 970 | else: |
6febd1c1 | 971 | self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn) |
7b6fefc9 | 972 | try: |
1538eff6 | 973 | write_json_file(info_dict, encodeFilename(infofn)) |
7b6fefc9 | 974 | except (OSError, IOError): |
6febd1c1 | 975 | self.report_error('Cannot write metadata to JSON file ' + infofn) |
7b6fefc9 | 976 | return |
8222d8de JMF |
977 | |
978 | if self.params.get('writethumbnail', False): | |
d8269e1d | 979 | if info_dict.get('thumbnail') is not None: |
6febd1c1 PH |
980 | thumb_format = determine_ext(info_dict['thumbnail'], 'jpg') |
981 | thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format | |
0a9ce268 | 982 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)): |
6febd1c1 | 983 | self.to_screen('[%s] %s: Thumbnail is already present' % |
7b6fefc9 PH |
984 | (info_dict['extractor'], info_dict['id'])) |
985 | else: | |
6febd1c1 | 986 | self.to_screen('[%s] %s: Downloading thumbnail ...' % |
7b6fefc9 PH |
987 | (info_dict['extractor'], info_dict['id'])) |
988 | try: | |
e9c092f1 | 989 | uf = self.urlopen(info_dict['thumbnail']) |
7b6fefc9 PH |
990 | with open(thumb_filename, 'wb') as thumbf: |
991 | shutil.copyfileobj(uf, thumbf) | |
6febd1c1 | 992 | self.to_screen('[%s] %s: Writing thumbnail to: %s' % |
7b6fefc9 PH |
993 | (info_dict['extractor'], info_dict['id'], thumb_filename)) |
994 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
6febd1c1 | 995 | self.report_warning('Unable to download thumbnail "%s": %s' % |
7b6fefc9 | 996 | (info_dict['thumbnail'], compat_str(err))) |
8222d8de JMF |
997 | |
998 | if not self.params.get('skip_download', False): | |
999 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): | |
1000 | success = True | |
1001 | else: | |
1002 | try: | |
6350728b JMF |
1003 | def dl(name, info): |
1004 | fd = get_suitable_downloader(info)(self, self.params) | |
1005 | for ph in self._progress_hooks: | |
1006 | fd.add_progress_hook(ph) | |
8d5797b0 PH |
1007 | if self.params.get('verbose'): |
1008 | self.to_stdout('[debug] Invoking downloader on %r' % info.get('url')) | |
6350728b JMF |
1009 | return fd.download(name, info) |
1010 | if info_dict.get('requested_formats') is not None: | |
1011 | downloaded = [] | |
1012 | success = True | |
b7f81164 | 1013 | merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) |
58c3c7ae JMF |
1014 | if not merger._get_executable(): |
1015 | postprocessors = [] | |
1016 | self.report_warning('You have requested multiple ' | |
1017 | 'formats but ffmpeg or avconv are not installed.' | |
1018 | ' The formats won\'t be merged') | |
1019 | else: | |
1020 | postprocessors = [merger] | |
6350728b JMF |
1021 | for f in info_dict['requested_formats']: |
1022 | new_info = dict(info_dict) | |
1023 | new_info.update(f) | |
1024 | fname = self.prepare_filename(new_info) | |
1025 | fname = prepend_extension(fname, 'f%s' % f['format_id']) | |
1026 | downloaded.append(fname) | |
1027 | partial_success = dl(fname, new_info) | |
1028 | success = success and partial_success | |
58c3c7ae | 1029 | info_dict['__postprocessors'] = postprocessors |
6350728b JMF |
1030 | info_dict['__files_to_merge'] = downloaded |
1031 | else: | |
1032 | # Just a single file | |
1033 | success = dl(filename, info_dict) | |
8222d8de | 1034 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
6febd1c1 | 1035 | self.report_error('unable to download video data: %s' % str(err)) |
8222d8de | 1036 | return |
c40c6aaa JMF |
1037 | except (OSError, IOError) as err: |
1038 | raise UnavailableVideoError(err) | |
8222d8de | 1039 | except (ContentTooShortError, ) as err: |
6febd1c1 | 1040 | self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) |
8222d8de JMF |
1041 | return |
1042 | ||
1043 | if success: | |
1044 | try: | |
1045 | self.post_process(filename, info_dict) | |
1046 | except (PostProcessingError) as err: | |
6febd1c1 | 1047 | self.report_error('postprocessing: %s' % str(err)) |
8222d8de JMF |
1048 | return |
1049 | ||
c1c9a79c PH |
1050 | self.record_download_archive(info_dict) |
1051 | ||
8222d8de JMF |
1052 | def download(self, url_list): |
1053 | """Download a given list of URLs.""" | |
acd69589 | 1054 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
0c75c3fa | 1055 | if (len(url_list) > 1 and |
acd69589 | 1056 | '%' not in outtmpl |
0c75c3fa | 1057 | and self.params.get('max_downloads') != 1): |
acd69589 | 1058 | raise SameFileError(outtmpl) |
8222d8de JMF |
1059 | |
1060 | for url in url_list: | |
1061 | try: | |
1062 | #It also downloads the videos | |
dca08720 | 1063 | self.extract_info(url) |
8222d8de | 1064 | except UnavailableVideoError: |
6febd1c1 | 1065 | self.report_error('unable to download video') |
8222d8de | 1066 | except MaxDownloadsReached: |
6febd1c1 | 1067 | self.to_screen('[info] Maximum number of downloaded files reached.') |
8222d8de JMF |
1068 | raise |
1069 | ||
1070 | return self._download_retcode | |
1071 | ||
1dcc4c0c | 1072 | def download_with_info_file(self, info_filename): |
395293a8 | 1073 | with io.open(info_filename, 'r', encoding='utf-8') as f: |
1dcc4c0c | 1074 | info = json.load(f) |
d4943898 JMF |
1075 | try: |
1076 | self.process_ie_result(info, download=True) | |
1077 | except DownloadError: | |
1078 | webpage_url = info.get('webpage_url') | |
1079 | if webpage_url is not None: | |
6febd1c1 | 1080 | self.report_warning('The info failed to download, trying with "%s"' % webpage_url) |
d4943898 JMF |
1081 | return self.download([webpage_url]) |
1082 | else: | |
1083 | raise | |
1084 | return self._download_retcode | |
1dcc4c0c | 1085 | |
8222d8de JMF |
1086 | def post_process(self, filename, ie_info): |
1087 | """Run all the postprocessors on the given file.""" | |
1088 | info = dict(ie_info) | |
1089 | info['filepath'] = filename | |
1090 | keep_video = None | |
6350728b JMF |
1091 | pps_chain = [] |
1092 | if ie_info.get('__postprocessors') is not None: | |
1093 | pps_chain.extend(ie_info['__postprocessors']) | |
1094 | pps_chain.extend(self._pps) | |
1095 | for pp in pps_chain: | |
8222d8de | 1096 | try: |
fe7e0c98 | 1097 | keep_video_wish, new_info = pp.run(info) |
8222d8de JMF |
1098 | if keep_video_wish is not None: |
1099 | if keep_video_wish: | |
1100 | keep_video = keep_video_wish | |
1101 | elif keep_video is None: | |
1102 | # No clear decision yet, let IE decide | |
1103 | keep_video = keep_video_wish | |
1104 | except PostProcessingError as e: | |
bbcbf4d4 | 1105 | self.report_error(e.msg) |
8222d8de JMF |
1106 | if keep_video is False and not self.params.get('keepvideo', False): |
1107 | try: | |
6febd1c1 | 1108 | self.to_screen('Deleting original file %s (pass -k to keep)' % filename) |
8222d8de JMF |
1109 | os.remove(encodeFilename(filename)) |
1110 | except (IOError, OSError): | |
6febd1c1 | 1111 | self.report_warning('Unable to remove downloaded video file') |
c1c9a79c | 1112 | |
5db07df6 PH |
1113 | def _make_archive_id(self, info_dict): |
1114 | # Future-proof against any change in case | |
1115 | # and backwards compatibility with prior versions | |
d31209a1 | 1116 | extractor = info_dict.get('extractor_key') |
7012b23c PH |
1117 | if extractor is None: |
1118 | if 'id' in info_dict: | |
1119 | extractor = info_dict.get('ie_key') # key in a playlist | |
1120 | if extractor is None: | |
5db07df6 | 1121 | return None # Incomplete video information |
6febd1c1 | 1122 | return extractor.lower() + ' ' + info_dict['id'] |
5db07df6 PH |
1123 | |
1124 | def in_download_archive(self, info_dict): | |
1125 | fn = self.params.get('download_archive') | |
1126 | if fn is None: | |
1127 | return False | |
1128 | ||
1129 | vid_id = self._make_archive_id(info_dict) | |
1130 | if vid_id is None: | |
7012b23c | 1131 | return False # Incomplete video information |
5db07df6 | 1132 | |
c1c9a79c PH |
1133 | try: |
1134 | with locked_file(fn, 'r', encoding='utf-8') as archive_file: | |
1135 | for line in archive_file: | |
1136 | if line.strip() == vid_id: | |
1137 | return True | |
1138 | except IOError as ioe: | |
1139 | if ioe.errno != errno.ENOENT: | |
1140 | raise | |
1141 | return False | |
1142 | ||
1143 | def record_download_archive(self, info_dict): | |
1144 | fn = self.params.get('download_archive') | |
1145 | if fn is None: | |
1146 | return | |
5db07df6 PH |
1147 | vid_id = self._make_archive_id(info_dict) |
1148 | assert vid_id | |
c1c9a79c | 1149 | with locked_file(fn, 'a', encoding='utf-8') as archive_file: |
6febd1c1 | 1150 | archive_file.write(vid_id + '\n') |
dd82ffea | 1151 | |
8c51aa65 | 1152 | @staticmethod |
8abeeb94 | 1153 | def format_resolution(format, default='unknown'): |
fb04e403 PH |
1154 | if format.get('vcodec') == 'none': |
1155 | return 'audio only' | |
f49d89ee PH |
1156 | if format.get('resolution') is not None: |
1157 | return format['resolution'] | |
8c51aa65 JMF |
1158 | if format.get('height') is not None: |
1159 | if format.get('width') is not None: | |
6febd1c1 | 1160 | res = '%sx%s' % (format['width'], format['height']) |
8c51aa65 | 1161 | else: |
6febd1c1 | 1162 | res = '%sp' % format['height'] |
f49d89ee | 1163 | elif format.get('width') is not None: |
6febd1c1 | 1164 | res = '?x%d' % format['width'] |
8c51aa65 | 1165 | else: |
8abeeb94 | 1166 | res = default |
8c51aa65 JMF |
1167 | return res |
1168 | ||
c57f7757 PH |
1169 | def _format_note(self, fdict): |
1170 | res = '' | |
1171 | if fdict.get('ext') in ['f4f', 'f4m']: | |
1172 | res += '(unsupported) ' | |
1173 | if fdict.get('format_note') is not None: | |
1174 | res += fdict['format_note'] + ' ' | |
1175 | if fdict.get('tbr') is not None: | |
1176 | res += '%4dk ' % fdict['tbr'] | |
1177 | if fdict.get('container') is not None: | |
1178 | if res: | |
1179 | res += ', ' | |
1180 | res += '%s container' % fdict['container'] | |
1181 | if (fdict.get('vcodec') is not None and | |
1182 | fdict.get('vcodec') != 'none'): | |
1183 | if res: | |
1184 | res += ', ' | |
1185 | res += fdict['vcodec'] | |
91c7271a | 1186 | if fdict.get('vbr') is not None: |
c57f7757 PH |
1187 | res += '@' |
1188 | elif fdict.get('vbr') is not None and fdict.get('abr') is not None: | |
1189 | res += 'video@' | |
1190 | if fdict.get('vbr') is not None: | |
1191 | res += '%4dk' % fdict['vbr'] | |
1192 | if fdict.get('acodec') is not None: | |
1193 | if res: | |
1194 | res += ', ' | |
1195 | if fdict['acodec'] == 'none': | |
1196 | res += 'video only' | |
1197 | else: | |
1198 | res += '%-5s' % fdict['acodec'] | |
1199 | elif fdict.get('abr') is not None: | |
1200 | if res: | |
1201 | res += ', ' | |
1202 | res += 'audio' | |
1203 | if fdict.get('abr') is not None: | |
1204 | res += '@%3dk' % fdict['abr'] | |
1205 | if fdict.get('asr') is not None: | |
1206 | res += ' (%5dHz)' % fdict['asr'] | |
1207 | if fdict.get('filesize') is not None: | |
1208 | if res: | |
1209 | res += ', ' | |
1210 | res += format_bytes(fdict['filesize']) | |
9732d77e PH |
1211 | elif fdict.get('filesize_approx') is not None: |
1212 | if res: | |
1213 | res += ', ' | |
1214 | res += '~' + format_bytes(fdict['filesize_approx']) | |
c57f7757 | 1215 | return res |
91c7271a | 1216 | |
c57f7757 | 1217 | def list_formats(self, info_dict): |
02dbf93f | 1218 | def line(format, idlen=20): |
6febd1c1 | 1219 | return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % ( |
8c51aa65 JMF |
1220 | format['format_id'], |
1221 | format['ext'], | |
8c51aa65 | 1222 | self.format_resolution(format), |
c57f7757 | 1223 | self._format_note(format), |
02dbf93f | 1224 | )) |
57dd9a8f | 1225 | |
94badb25 | 1226 | formats = info_dict.get('formats', [info_dict]) |
6febd1c1 | 1227 | idlen = max(len('format code'), |
02dbf93f PH |
1228 | max(len(f['format_id']) for f in formats)) |
1229 | formats_s = [line(f, idlen) for f in formats] | |
94badb25 | 1230 | if len(formats) > 1: |
c57f7757 PH |
1231 | formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)' |
1232 | formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)' | |
57dd9a8f PH |
1233 | |
1234 | header_line = line({ | |
6febd1c1 PH |
1235 | 'format_id': 'format code', 'ext': 'extension', |
1236 | 'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen) | |
1237 | self.to_screen('[info] Available formats for %s:\n%s\n%s' % | |
1238 | (info_dict['id'], header_line, '\n'.join(formats_s))) | |
dca08720 PH |
1239 | |
1240 | def urlopen(self, req): | |
1241 | """ Start an HTTP download """ | |
19a41fc6 | 1242 | return self._opener.open(req, timeout=self._socket_timeout) |
dca08720 PH |
1243 | |
1244 | def print_debug_header(self): | |
1245 | if not self.params.get('verbose'): | |
1246 | return | |
62fec3b2 | 1247 | |
4192b51c PH |
1248 | if type('') is not compat_str: |
1249 | # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326) | |
1250 | self.report_warning( | |
1251 | 'Your Python is broken! Update to a newer and supported version') | |
1252 | ||
b0472057 | 1253 | encoding_str = ( |
734f90bb PH |
1254 | '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( |
1255 | locale.getpreferredencoding(), | |
1256 | sys.getfilesystemencoding(), | |
1257 | sys.stdout.encoding, | |
b0472057 | 1258 | self.get_encoding())) |
4192b51c | 1259 | write_string(encoding_str, encoding=None) |
734f90bb PH |
1260 | |
1261 | self._write_string('[debug] youtube-dl version ' + __version__ + '\n') | |
dca08720 PH |
1262 | try: |
1263 | sp = subprocess.Popen( | |
1264 | ['git', 'rev-parse', '--short', 'HEAD'], | |
1265 | stdout=subprocess.PIPE, stderr=subprocess.PIPE, | |
1266 | cwd=os.path.dirname(os.path.abspath(__file__))) | |
1267 | out, err = sp.communicate() | |
1268 | out = out.decode().strip() | |
1269 | if re.match('[0-9a-f]+', out): | |
734f90bb | 1270 | self._write_string('[debug] Git HEAD: ' + out + '\n') |
dca08720 PH |
1271 | except: |
1272 | try: | |
1273 | sys.exc_clear() | |
1274 | except: | |
1275 | pass | |
734f90bb | 1276 | self._write_string('[debug] Python version %s - %s' % |
6febd1c1 | 1277 | (platform.python_version(), platform_name()) + '\n') |
dca08720 PH |
1278 | |
1279 | proxy_map = {} | |
1280 | for handler in self._opener.handlers: | |
1281 | if hasattr(handler, 'proxies'): | |
1282 | proxy_map.update(handler.proxies) | |
734f90bb | 1283 | self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') |
dca08720 | 1284 | |
e344693b | 1285 | def _setup_opener(self): |
6ad14cab | 1286 | timeout_val = self.params.get('socket_timeout') |
19a41fc6 | 1287 | self._socket_timeout = 600 if timeout_val is None else float(timeout_val) |
6ad14cab | 1288 | |
dca08720 PH |
1289 | opts_cookiefile = self.params.get('cookiefile') |
1290 | opts_proxy = self.params.get('proxy') | |
1291 | ||
1292 | if opts_cookiefile is None: | |
1293 | self.cookiejar = compat_cookiejar.CookieJar() | |
1294 | else: | |
1295 | self.cookiejar = compat_cookiejar.MozillaCookieJar( | |
1296 | opts_cookiefile) | |
1297 | if os.access(opts_cookiefile, os.R_OK): | |
1298 | self.cookiejar.load() | |
1299 | ||
1300 | cookie_processor = compat_urllib_request.HTTPCookieProcessor( | |
1301 | self.cookiejar) | |
1302 | if opts_proxy is not None: | |
1303 | if opts_proxy == '': | |
1304 | proxies = {} | |
1305 | else: | |
1306 | proxies = {'http': opts_proxy, 'https': opts_proxy} | |
1307 | else: | |
1308 | proxies = compat_urllib_request.getproxies() | |
1309 | # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) | |
1310 | if 'http' in proxies and 'https' not in proxies: | |
1311 | proxies['https'] = proxies['http'] | |
1312 | proxy_handler = compat_urllib_request.ProxyHandler(proxies) | |
a0ddb8a2 PH |
1313 | |
1314 | debuglevel = 1 if self.params.get('debug_printtraffic') else 0 | |
dca08720 | 1315 | https_handler = make_HTTPS_handler( |
a0ddb8a2 PH |
1316 | self.params.get('nocheckcertificate', False), debuglevel=debuglevel) |
1317 | ydlh = YoutubeDLHandler(debuglevel=debuglevel) | |
dca08720 | 1318 | opener = compat_urllib_request.build_opener( |
a0ddb8a2 | 1319 | https_handler, proxy_handler, cookie_processor, ydlh) |
dca08720 PH |
1320 | # Delete the default user-agent header, which would otherwise apply in |
1321 | # cases where our custom HTTP handler doesn't come into play | |
1322 | # (See https://github.com/rg3/youtube-dl/issues/1309 for details) | |
1323 | opener.addheaders = [] | |
1324 | self._opener = opener | |
62fec3b2 PH |
1325 | |
1326 | def encode(self, s): | |
1327 | if isinstance(s, bytes): | |
1328 | return s # Already encoded | |
1329 | ||
1330 | try: | |
1331 | return s.encode(self.get_encoding()) | |
1332 | except UnicodeEncodeError as err: | |
1333 | err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.' | |
1334 | raise | |
1335 | ||
1336 | def get_encoding(self): | |
1337 | encoding = self.params.get('encoding') | |
1338 | if encoding is None: | |
1339 | encoding = preferredencoding() | |
1340 | return encoding |