]>
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. |
fe7e0c98 | 165 | |
8222d8de JMF |
166 | The following parameters are not used by YoutubeDL itself, they are used by |
167 | the FileDownloader: | |
168 | nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, | |
169 | noresizebuffer, retries, continuedl, noprogress, consoletitle | |
76b1bd67 JMF |
170 | |
171 | The following options are used by the post processors: | |
172 | prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, | |
173 | otherwise prefer avconv. | |
8222d8de JMF |
174 | """ |
175 | ||
176 | params = None | |
177 | _ies = [] | |
178 | _pps = [] | |
179 | _download_retcode = None | |
180 | _num_downloads = None | |
181 | _screen_file = None | |
182 | ||
a3fb4675 | 183 | def __init__(self, params=None): |
8222d8de | 184 | """Create a FileDownloader object with the given options.""" |
e9f9a10f JMF |
185 | if params is None: |
186 | params = {} | |
8222d8de | 187 | self._ies = [] |
56c73665 | 188 | self._ies_instances = {} |
8222d8de | 189 | self._pps = [] |
933605d7 | 190 | self._progress_hooks = [] |
8222d8de JMF |
191 | self._download_retcode = 0 |
192 | self._num_downloads = 0 | |
193 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] | |
0783b09b | 194 | self._err_file = sys.stderr |
e9f9a10f | 195 | self.params = params |
34308b30 | 196 | |
0783b09b | 197 | if params.get('bidi_workaround', False): |
1c088fa8 PH |
198 | try: |
199 | import pty | |
200 | master, slave = pty.openpty() | |
201 | width = get_term_width() | |
202 | if width is None: | |
203 | width_args = [] | |
204 | else: | |
205 | width_args = ['-w', str(width)] | |
5d681e96 | 206 | sp_kwargs = dict( |
1c088fa8 PH |
207 | stdin=subprocess.PIPE, |
208 | stdout=slave, | |
209 | stderr=self._err_file) | |
5d681e96 PH |
210 | try: |
211 | self._output_process = subprocess.Popen( | |
212 | ['bidiv'] + width_args, **sp_kwargs | |
213 | ) | |
214 | except OSError: | |
5d681e96 PH |
215 | self._output_process = subprocess.Popen( |
216 | ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) | |
217 | self._output_channel = os.fdopen(master, 'rb') | |
1c088fa8 PH |
218 | except OSError as ose: |
219 | if ose.errno == 2: | |
6febd1c1 | 220 | 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 |
221 | else: |
222 | raise | |
0783b09b | 223 | |
34308b30 PH |
224 | if (sys.version_info >= (3,) and sys.platform != 'win32' and |
225 | sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] | |
226 | and not params['restrictfilenames']): | |
227 | # On Python 3, the Unicode filesystem API will throw errors (#1474) | |
228 | self.report_warning( | |
6febd1c1 PH |
229 | 'Assuming --restrict-filenames since file system encoding ' |
230 | 'cannot encode all charactes. ' | |
231 | 'Set the LC_ALL environment variable to fix this.') | |
4a98cdbf | 232 | self.params['restrictfilenames'] = True |
34308b30 | 233 | |
a3927cf7 | 234 | if '%(stitle)s' in self.params.get('outtmpl', ''): |
6febd1c1 | 235 | 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 | 236 | |
dca08720 PH |
237 | self._setup_opener() |
238 | ||
8222d8de JMF |
239 | def add_info_extractor(self, ie): |
240 | """Add an InfoExtractor object to the end of the list.""" | |
241 | self._ies.append(ie) | |
56c73665 | 242 | self._ies_instances[ie.ie_key()] = ie |
8222d8de JMF |
243 | ie.set_downloader(self) |
244 | ||
56c73665 JMF |
245 | def get_info_extractor(self, ie_key): |
246 | """ | |
247 | Get an instance of an IE with name ie_key, it will try to get one from | |
248 | the _ies list, if there's no instance it will create a new one and add | |
249 | it to the extractor list. | |
250 | """ | |
251 | ie = self._ies_instances.get(ie_key) | |
252 | if ie is None: | |
253 | ie = get_info_extractor(ie_key)() | |
254 | self.add_info_extractor(ie) | |
255 | return ie | |
256 | ||
023fa8c4 JMF |
257 | def add_default_info_extractors(self): |
258 | """ | |
259 | Add the InfoExtractors returned by gen_extractors to the end of the list | |
260 | """ | |
261 | for ie in gen_extractors(): | |
262 | self.add_info_extractor(ie) | |
263 | ||
8222d8de JMF |
264 | def add_post_processor(self, pp): |
265 | """Add a PostProcessor object to the end of the chain.""" | |
266 | self._pps.append(pp) | |
267 | pp.set_downloader(self) | |
268 | ||
933605d7 JMF |
269 | def add_progress_hook(self, ph): |
270 | """Add the progress hook (currently only for the file downloader)""" | |
271 | self._progress_hooks.append(ph) | |
8ab470f1 | 272 | |
1c088fa8 | 273 | def _bidi_workaround(self, message): |
5d681e96 | 274 | if not hasattr(self, '_output_channel'): |
1c088fa8 PH |
275 | return message |
276 | ||
5d681e96 | 277 | assert hasattr(self, '_output_process') |
6febd1c1 PH |
278 | assert type(message) == type('') |
279 | line_count = message.count('\n') + 1 | |
280 | self._output_process.stdin.write((message + '\n').encode('utf-8')) | |
5d681e96 | 281 | self._output_process.stdin.flush() |
6febd1c1 | 282 | res = ''.join(self._output_channel.readline().decode('utf-8') |
1c088fa8 | 283 | for _ in range(line_count)) |
6febd1c1 | 284 | return res[:-len('\n')] |
1c088fa8 | 285 | |
8222d8de | 286 | def to_screen(self, message, skip_eol=False): |
0783b09b PH |
287 | """Print message to stdout if not in quiet mode.""" |
288 | return self.to_stdout(message, skip_eol, check_quiet=True) | |
289 | ||
734f90bb | 290 | def _write_string(self, s, out=None): |
b58ddb32 | 291 | write_string(s, out=out, encoding=self.params.get('encoding')) |
734f90bb | 292 | |
0783b09b | 293 | def to_stdout(self, message, skip_eol=False, check_quiet=False): |
8222d8de | 294 | """Print message to stdout if not in quiet mode.""" |
8bf9319e | 295 | if self.params.get('logger'): |
43afe285 | 296 | self.params['logger'].debug(message) |
0783b09b | 297 | elif not check_quiet or not self.params.get('quiet', False): |
1c088fa8 | 298 | message = self._bidi_workaround(message) |
6febd1c1 | 299 | terminator = ['\n', ''][skip_eol] |
8222d8de | 300 | output = message + terminator |
1c088fa8 | 301 | |
734f90bb | 302 | self._write_string(output, self._screen_file) |
8222d8de JMF |
303 | |
304 | def to_stderr(self, message): | |
305 | """Print message to stderr.""" | |
6febd1c1 | 306 | assert type(message) == type('') |
8bf9319e | 307 | if self.params.get('logger'): |
43afe285 IB |
308 | self.params['logger'].error(message) |
309 | else: | |
1c088fa8 | 310 | message = self._bidi_workaround(message) |
6febd1c1 | 311 | output = message + '\n' |
734f90bb | 312 | self._write_string(output, self._err_file) |
8222d8de | 313 | |
1e5b9a95 PH |
314 | def to_console_title(self, message): |
315 | if not self.params.get('consoletitle', False): | |
316 | return | |
317 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
318 | # c_wchar_p() might not be necessary if `message` is | |
319 | # already of type unicode() | |
320 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
321 | elif 'TERM' in os.environ: | |
734f90bb | 322 | self._write_string('\033]0;%s\007' % message, self._screen_file) |
1e5b9a95 | 323 | |
bdde425c PH |
324 | def save_console_title(self): |
325 | if not self.params.get('consoletitle', False): | |
326 | return | |
327 | if 'TERM' in os.environ: | |
efd6c574 | 328 | # Save the title on stack |
734f90bb | 329 | self._write_string('\033[22;0t', self._screen_file) |
bdde425c PH |
330 | |
331 | def restore_console_title(self): | |
332 | if not self.params.get('consoletitle', False): | |
333 | return | |
334 | if 'TERM' in os.environ: | |
efd6c574 | 335 | # Restore the title from stack |
734f90bb | 336 | self._write_string('\033[23;0t', self._screen_file) |
bdde425c PH |
337 | |
338 | def __enter__(self): | |
339 | self.save_console_title() | |
340 | return self | |
341 | ||
342 | def __exit__(self, *args): | |
343 | self.restore_console_title() | |
f89197d7 | 344 | |
dca08720 PH |
345 | if self.params.get('cookiefile') is not None: |
346 | self.cookiejar.save() | |
bdde425c | 347 | |
8222d8de JMF |
348 | def trouble(self, message=None, tb=None): |
349 | """Determine action to take when a download problem appears. | |
350 | ||
351 | Depending on if the downloader has been configured to ignore | |
352 | download errors or not, this method may throw an exception or | |
353 | not when errors are found, after printing the message. | |
354 | ||
355 | tb, if given, is additional traceback information. | |
356 | """ | |
357 | if message is not None: | |
358 | self.to_stderr(message) | |
359 | if self.params.get('verbose'): | |
360 | if tb is None: | |
361 | if sys.exc_info()[0]: # if .trouble has been called from an except block | |
6febd1c1 | 362 | tb = '' |
8222d8de | 363 | if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: |
6febd1c1 | 364 | tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) |
8222d8de JMF |
365 | tb += compat_str(traceback.format_exc()) |
366 | else: | |
367 | tb_data = traceback.format_list(traceback.extract_stack()) | |
6febd1c1 | 368 | tb = ''.join(tb_data) |
8222d8de JMF |
369 | self.to_stderr(tb) |
370 | if not self.params.get('ignoreerrors', False): | |
371 | if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: | |
372 | exc_info = sys.exc_info()[1].exc_info | |
373 | else: | |
374 | exc_info = sys.exc_info() | |
375 | raise DownloadError(message, exc_info) | |
376 | self._download_retcode = 1 | |
377 | ||
378 | def report_warning(self, message): | |
379 | ''' | |
380 | Print the message to stderr, it will be prefixed with 'WARNING:' | |
381 | If stderr is a tty file the 'WARNING:' will be colored | |
382 | ''' | |
6d07ce01 JMF |
383 | if self.params.get('logger') is not None: |
384 | self.params['logger'].warning(message) | |
8222d8de | 385 | else: |
ad8915b7 PH |
386 | if self.params.get('no_warnings'): |
387 | return | |
6d07ce01 JMF |
388 | if self._err_file.isatty() and os.name != 'nt': |
389 | _msg_header = '\033[0;33mWARNING:\033[0m' | |
390 | else: | |
391 | _msg_header = 'WARNING:' | |
392 | warning_message = '%s %s' % (_msg_header, message) | |
393 | self.to_stderr(warning_message) | |
8222d8de JMF |
394 | |
395 | def report_error(self, message, tb=None): | |
396 | ''' | |
397 | Do the same as trouble, but prefixes the message with 'ERROR:', colored | |
398 | in red if stderr is a tty file. | |
399 | ''' | |
0783b09b | 400 | if self._err_file.isatty() and os.name != 'nt': |
6febd1c1 | 401 | _msg_header = '\033[0;31mERROR:\033[0m' |
8222d8de | 402 | else: |
6febd1c1 PH |
403 | _msg_header = 'ERROR:' |
404 | error_message = '%s %s' % (_msg_header, message) | |
8222d8de JMF |
405 | self.trouble(error_message, tb) |
406 | ||
8222d8de JMF |
407 | def report_file_already_downloaded(self, file_name): |
408 | """Report file has already been fully downloaded.""" | |
409 | try: | |
6febd1c1 | 410 | self.to_screen('[download] %s has already been downloaded' % file_name) |
ce02ed60 | 411 | except UnicodeEncodeError: |
6febd1c1 | 412 | self.to_screen('[download] The file has already been downloaded') |
8222d8de | 413 | |
8222d8de JMF |
414 | def prepare_filename(self, info_dict): |
415 | """Generate the output filename.""" | |
416 | try: | |
417 | template_dict = dict(info_dict) | |
418 | ||
419 | template_dict['epoch'] = int(time.time()) | |
420 | autonumber_size = self.params.get('autonumber_size') | |
421 | if autonumber_size is None: | |
422 | autonumber_size = 5 | |
6febd1c1 | 423 | autonumber_templ = '%0' + str(autonumber_size) + 'd' |
8222d8de | 424 | template_dict['autonumber'] = autonumber_templ % self._num_downloads |
702665c0 | 425 | if template_dict.get('playlist_index') is not None: |
6febd1c1 | 426 | template_dict['playlist_index'] = '%05d' % template_dict['playlist_index'] |
17b75c0d PH |
427 | if template_dict.get('resolution') is None: |
428 | if template_dict.get('width') and template_dict.get('height'): | |
429 | template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height']) | |
430 | elif template_dict.get('height'): | |
805ef3c6 | 431 | template_dict['resolution'] = '%sp' % template_dict['height'] |
17b75c0d | 432 | elif template_dict.get('width'): |
805ef3c6 | 433 | template_dict['resolution'] = '?x%d' % template_dict['width'] |
8222d8de | 434 | |
586a91b6 | 435 | sanitize = lambda k, v: sanitize_filename( |
45598aab | 436 | compat_str(v), |
8222d8de | 437 | restricted=self.params.get('restrictfilenames'), |
6febd1c1 | 438 | is_id=(k == 'id')) |
586a91b6 | 439 | template_dict = dict((k, sanitize(k, v)) |
45598aab PH |
440 | for k, v in template_dict.items() |
441 | if v is not None) | |
6febd1c1 | 442 | template_dict = collections.defaultdict(lambda: 'NA', template_dict) |
8222d8de | 443 | |
acd69589 PH |
444 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
445 | tmpl = os.path.expanduser(outtmpl) | |
586a91b6 | 446 | filename = tmpl % template_dict |
8222d8de | 447 | return filename |
8222d8de | 448 | except ValueError as err: |
6febd1c1 | 449 | self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') |
8222d8de JMF |
450 | return None |
451 | ||
452 | def _match_entry(self, info_dict): | |
453 | """ Returns None iff the file should be downloaded """ | |
454 | ||
6febd1c1 | 455 | video_title = info_dict.get('title', info_dict.get('id', 'video')) |
7012b23c PH |
456 | if 'title' in info_dict: |
457 | # This can happen when we're just evaluating the playlist | |
458 | title = info_dict['title'] | |
459 | matchtitle = self.params.get('matchtitle', False) | |
460 | if matchtitle: | |
461 | if not re.search(matchtitle, title, re.IGNORECASE): | |
6febd1c1 | 462 | return '"' + title + '" title did not match pattern "' + matchtitle + '"' |
7012b23c PH |
463 | rejecttitle = self.params.get('rejecttitle', False) |
464 | if rejecttitle: | |
465 | if re.search(rejecttitle, title, re.IGNORECASE): | |
6febd1c1 | 466 | return '"' + title + '" title matched reject pattern "' + rejecttitle + '"' |
8222d8de JMF |
467 | date = info_dict.get('upload_date', None) |
468 | if date is not None: | |
469 | dateRange = self.params.get('daterange', DateRange()) | |
470 | if date not in dateRange: | |
6febd1c1 | 471 | return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) |
5fe18bdb PH |
472 | view_count = info_dict.get('view_count', None) |
473 | if view_count is not None: | |
474 | min_views = self.params.get('min_views') | |
475 | if min_views is not None and view_count < min_views: | |
6febd1c1 | 476 | return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views) |
5fe18bdb PH |
477 | max_views = self.params.get('max_views') |
478 | if max_views is not None and view_count > max_views: | |
6febd1c1 | 479 | return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) |
8dbe9899 PH |
480 | age_limit = self.params.get('age_limit') |
481 | if age_limit is not None: | |
cfadd183 | 482 | if age_limit < info_dict.get('age_limit', 0): |
6febd1c1 | 483 | return 'Skipping "' + title + '" because it is age restricted' |
c1c9a79c | 484 | if self.in_download_archive(info_dict): |
6febd1c1 | 485 | return '%s has already been recorded in archive' % video_title |
8222d8de | 486 | return None |
fe7e0c98 | 487 | |
b6c45014 JMF |
488 | @staticmethod |
489 | def add_extra_info(info_dict, extra_info): | |
490 | '''Set the keys from extra_info in info dict if they are missing''' | |
491 | for key, value in extra_info.items(): | |
492 | info_dict.setdefault(key, value) | |
493 | ||
7fc3fa05 PH |
494 | def extract_info(self, url, download=True, ie_key=None, extra_info={}, |
495 | process=True): | |
8222d8de JMF |
496 | ''' |
497 | Returns a list with a dictionary for each video we find. | |
498 | If 'download', also downloads the videos. | |
499 | extra_info is a dict containing the extra values to add to each result | |
500 | ''' | |
fe7e0c98 | 501 | |
8222d8de | 502 | if ie_key: |
56c73665 | 503 | ies = [self.get_info_extractor(ie_key)] |
8222d8de JMF |
504 | else: |
505 | ies = self._ies | |
506 | ||
507 | for ie in ies: | |
508 | if not ie.suitable(url): | |
509 | continue | |
510 | ||
511 | if not ie.working(): | |
6febd1c1 PH |
512 | self.report_warning('The program functionality for this site has been marked as broken, ' |
513 | 'and will probably not work.') | |
8222d8de JMF |
514 | |
515 | try: | |
516 | ie_result = ie.extract(url) | |
517 | if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) | |
518 | break | |
519 | if isinstance(ie_result, list): | |
520 | # Backwards compatibility: old IE result format | |
8222d8de JMF |
521 | ie_result = { |
522 | '_type': 'compat_list', | |
523 | 'entries': ie_result, | |
524 | } | |
ea38e55f | 525 | self.add_default_extra_info(ie_result, ie, url) |
7fc3fa05 PH |
526 | if process: |
527 | return self.process_ie_result(ie_result, download, extra_info) | |
528 | else: | |
529 | return ie_result | |
8222d8de JMF |
530 | except ExtractorError as de: # An error we somewhat expected |
531 | self.report_error(compat_str(de), de.format_traceback()) | |
532 | break | |
d3e5bbf4 PH |
533 | except MaxDownloadsReached: |
534 | raise | |
8222d8de JMF |
535 | except Exception as e: |
536 | if self.params.get('ignoreerrors', False): | |
537 | self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) | |
538 | break | |
539 | else: | |
540 | raise | |
541 | else: | |
1a489545 | 542 | self.report_error('no suitable InfoExtractor for URL %s' % url) |
fe7e0c98 | 543 | |
ea38e55f PH |
544 | def add_default_extra_info(self, ie_result, ie, url): |
545 | self.add_extra_info(ie_result, { | |
546 | 'extractor': ie.IE_NAME, | |
547 | 'webpage_url': url, | |
548 | 'webpage_url_basename': url_basename(url), | |
549 | 'extractor_key': ie.ie_key(), | |
550 | }) | |
551 | ||
8222d8de JMF |
552 | def process_ie_result(self, ie_result, download=True, extra_info={}): |
553 | """ | |
554 | Take the result of the ie(may be modified) and resolve all unresolved | |
555 | references (URLs, playlist items). | |
556 | ||
557 | It will also download the videos if 'download'. | |
558 | Returns the resolved ie_result. | |
559 | """ | |
560 | ||
561 | result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system | |
562 | if result_type == 'video': | |
b6c45014 | 563 | self.add_extra_info(ie_result, extra_info) |
feee2ecf | 564 | return self.process_video_result(ie_result, download=download) |
8222d8de JMF |
565 | elif result_type == 'url': |
566 | # We have to add extra_info to the results because it may be | |
567 | # contained in a playlist | |
568 | return self.extract_info(ie_result['url'], | |
569 | download, | |
570 | ie_key=ie_result.get('ie_key'), | |
571 | extra_info=extra_info) | |
7fc3fa05 PH |
572 | elif result_type == 'url_transparent': |
573 | # Use the information from the embedding page | |
574 | info = self.extract_info( | |
575 | ie_result['url'], ie_key=ie_result.get('ie_key'), | |
576 | extra_info=extra_info, download=False, process=False) | |
577 | ||
578 | def make_result(embedded_info): | |
579 | new_result = ie_result.copy() | |
580 | for f in ('_type', 'url', 'ext', 'player_url', 'formats', | |
1538eff6 | 581 | 'entries', 'ie_key', 'duration', |
ef4fd848 PH |
582 | 'subtitles', 'annotations', 'format', |
583 | 'thumbnail', 'thumbnails'): | |
7fc3fa05 PH |
584 | if f in new_result: |
585 | del new_result[f] | |
586 | if f in embedded_info: | |
587 | new_result[f] = embedded_info[f] | |
588 | return new_result | |
589 | new_result = make_result(info) | |
590 | ||
591 | assert new_result.get('_type') != 'url_transparent' | |
592 | if new_result.get('_type') == 'compat_list': | |
593 | new_result['entries'] = [ | |
594 | make_result(e) for e in new_result['entries']] | |
595 | ||
596 | return self.process_ie_result( | |
597 | new_result, download=download, extra_info=extra_info) | |
8222d8de JMF |
598 | elif result_type == 'playlist': |
599 | # We process each entry in the playlist | |
600 | playlist = ie_result.get('title', None) or ie_result.get('id', None) | |
6febd1c1 | 601 | self.to_screen('[download] Downloading playlist: %s' % playlist) |
8222d8de JMF |
602 | |
603 | playlist_results = [] | |
604 | ||
8222d8de | 605 | playliststart = self.params.get('playliststart', 1) - 1 |
a19fd00c PH |
606 | playlistend = self.params.get('playlistend', None) |
607 | # For backwards compatibility, interpret -1 as whole list | |
8222d8de | 608 | if playlistend == -1: |
a19fd00c | 609 | playlistend = None |
8222d8de | 610 | |
b7ab0590 PH |
611 | if isinstance(ie_result['entries'], list): |
612 | n_all_entries = len(ie_result['entries']) | |
613 | entries = ie_result['entries'][playliststart:playlistend] | |
614 | n_entries = len(entries) | |
615 | self.to_screen( | |
616 | "[%s] playlist %s: Collected %d video ids (downloading %d of them)" % | |
617 | (ie_result['extractor'], playlist, n_all_entries, n_entries)) | |
618 | else: | |
619 | assert isinstance(ie_result['entries'], PagedList) | |
620 | entries = ie_result['entries'].getslice( | |
621 | playliststart, playlistend) | |
622 | n_entries = len(entries) | |
623 | self.to_screen( | |
624 | "[%s] playlist %s: Downloading %d videos" % | |
625 | (ie_result['extractor'], playlist, n_entries)) | |
8222d8de | 626 | |
fe7e0c98 | 627 | for i, entry in enumerate(entries, 1): |
6febd1c1 | 628 | self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries)) |
8222d8de | 629 | extra = { |
fe7e0c98 JMF |
630 | 'playlist': playlist, |
631 | 'playlist_index': i + playliststart, | |
b6c45014 | 632 | 'extractor': ie_result['extractor'], |
9103bbc5 | 633 | 'webpage_url': ie_result['webpage_url'], |
29eb5174 | 634 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 635 | 'extractor_key': ie_result['extractor_key'], |
fe7e0c98 | 636 | } |
7012b23c PH |
637 | |
638 | reason = self._match_entry(entry) | |
639 | if reason is not None: | |
6febd1c1 | 640 | self.to_screen('[download] ' + reason) |
7012b23c PH |
641 | continue |
642 | ||
8222d8de JMF |
643 | entry_result = self.process_ie_result(entry, |
644 | download=download, | |
645 | extra_info=extra) | |
646 | playlist_results.append(entry_result) | |
647 | ie_result['entries'] = playlist_results | |
648 | return ie_result | |
649 | elif result_type == 'compat_list': | |
650 | def _fixup(r): | |
b6c45014 | 651 | self.add_extra_info(r, |
9103bbc5 JMF |
652 | { |
653 | 'extractor': ie_result['extractor'], | |
654 | 'webpage_url': ie_result['webpage_url'], | |
29eb5174 | 655 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 656 | 'extractor_key': ie_result['extractor_key'], |
9103bbc5 | 657 | }) |
8222d8de JMF |
658 | return r |
659 | ie_result['entries'] = [ | |
b6c45014 | 660 | self.process_ie_result(_fixup(r), download, extra_info) |
8222d8de JMF |
661 | for r in ie_result['entries'] |
662 | ] | |
663 | return ie_result | |
664 | else: | |
665 | raise Exception('Invalid result type: %s' % result_type) | |
666 | ||
a9c58ad9 JMF |
667 | def select_format(self, format_spec, available_formats): |
668 | if format_spec == 'best' or format_spec is None: | |
669 | return available_formats[-1] | |
670 | elif format_spec == 'worst': | |
671 | return available_formats[0] | |
ba7678f9 PH |
672 | elif format_spec == 'bestaudio': |
673 | audio_formats = [ | |
674 | f for f in available_formats | |
675 | if f.get('vcodec') == 'none'] | |
676 | if audio_formats: | |
677 | return audio_formats[-1] | |
678 | elif format_spec == 'worstaudio': | |
679 | audio_formats = [ | |
680 | f for f in available_formats | |
681 | if f.get('vcodec') == 'none'] | |
682 | if audio_formats: | |
683 | return audio_formats[0] | |
bc6d5978 JMF |
684 | elif format_spec == 'bestvideo': |
685 | video_formats = [ | |
686 | f for f in available_formats | |
687 | if f.get('acodec') == 'none'] | |
688 | if video_formats: | |
689 | return video_formats[-1] | |
690 | elif format_spec == 'worstvideo': | |
691 | video_formats = [ | |
692 | f for f in available_formats | |
693 | if f.get('acodec') == 'none'] | |
694 | if video_formats: | |
695 | return video_formats[0] | |
a9c58ad9 | 696 | else: |
6febd1c1 | 697 | extensions = ['mp4', 'flv', 'webm', '3gp'] |
49e86983 JMF |
698 | if format_spec in extensions: |
699 | filter_f = lambda f: f['ext'] == format_spec | |
700 | else: | |
701 | filter_f = lambda f: f['format_id'] == format_spec | |
fe7e0c98 | 702 | matches = list(filter(filter_f, available_formats)) |
a9c58ad9 JMF |
703 | if matches: |
704 | return matches[-1] | |
705 | return None | |
706 | ||
dd82ffea JMF |
707 | def process_video_result(self, info_dict, download=True): |
708 | assert info_dict.get('_type', 'video') == 'video' | |
709 | ||
bec1fad2 PH |
710 | if 'id' not in info_dict: |
711 | raise ExtractorError('Missing "id" field in extractor result') | |
712 | if 'title' not in info_dict: | |
713 | raise ExtractorError('Missing "title" field in extractor result') | |
714 | ||
dd82ffea JMF |
715 | if 'playlist' not in info_dict: |
716 | # It isn't part of a playlist | |
717 | info_dict['playlist'] = None | |
718 | info_dict['playlist_index'] = None | |
719 | ||
d5519808 PH |
720 | thumbnails = info_dict.get('thumbnails') |
721 | if thumbnails: | |
be6d7229 PH |
722 | thumbnails.sort(key=lambda t: ( |
723 | t.get('width'), t.get('height'), t.get('url'))) | |
d5519808 PH |
724 | for t in thumbnails: |
725 | if 'width' in t and 'height' in t: | |
726 | t['resolution'] = '%dx%d' % (t['width'], t['height']) | |
727 | ||
728 | if thumbnails and 'thumbnail' not in info_dict: | |
729 | info_dict['thumbnail'] = thumbnails[-1]['url'] | |
730 | ||
c9ae7b95 | 731 | if 'display_id' not in info_dict and 'id' in info_dict: |
0afef30b PH |
732 | info_dict['display_id'] = info_dict['id'] |
733 | ||
955c4514 | 734 | if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None: |
9d2ecdbc | 735 | upload_date = datetime.datetime.utcfromtimestamp( |
955c4514 | 736 | info_dict['timestamp']) |
9d2ecdbc PH |
737 | info_dict['upload_date'] = upload_date.strftime('%Y%m%d') |
738 | ||
6ff000b8 | 739 | # This extractors handle format selection themselves |
6febd1c1 | 740 | if info_dict['extractor'] in ['Youku']: |
12893efe JMF |
741 | if download: |
742 | self.process_info(info_dict) | |
6ff000b8 JMF |
743 | return info_dict |
744 | ||
dd82ffea JMF |
745 | # We now pick which formats have to be downloaded |
746 | if info_dict.get('formats') is None: | |
747 | # There's only one format available | |
748 | formats = [info_dict] | |
749 | else: | |
750 | formats = info_dict['formats'] | |
751 | ||
db95dc13 PH |
752 | if not formats: |
753 | raise ExtractorError('No video formats found!') | |
754 | ||
dd82ffea | 755 | # We check that all the formats have the format and format_id fields |
db95dc13 | 756 | for i, format in enumerate(formats): |
bec1fad2 PH |
757 | if 'url' not in format: |
758 | raise ExtractorError('Missing "url" key in result (index %d)' % i) | |
759 | ||
dd82ffea | 760 | if format.get('format_id') is None: |
8016c922 | 761 | format['format_id'] = compat_str(i) |
8c51aa65 | 762 | if format.get('format') is None: |
6febd1c1 | 763 | format['format'] = '{id} - {res}{note}'.format( |
8c51aa65 JMF |
764 | id=format['format_id'], |
765 | res=self.format_resolution(format), | |
6febd1c1 | 766 | note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', |
8c51aa65 | 767 | ) |
c1002e96 PH |
768 | # Automatically determine file extension if missing |
769 | if 'ext' not in format: | |
cce929ea | 770 | format['ext'] = determine_ext(format['url']).lower() |
dd82ffea | 771 | |
99e206d5 JMF |
772 | format_limit = self.params.get('format_limit', None) |
773 | if format_limit: | |
f4d96df0 PH |
774 | formats = list(takewhile_inclusive( |
775 | lambda f: f['format_id'] != format_limit, formats | |
776 | )) | |
4bcc7bd1 PH |
777 | |
778 | # TODO Central sorting goes here | |
99e206d5 | 779 | |
f89197d7 | 780 | if formats[0] is not info_dict: |
b3d9ef88 JMF |
781 | # only set the 'formats' fields if the original info_dict list them |
782 | # otherwise we end up with a circular reference, the first (and unique) | |
f89197d7 | 783 | # element in the 'formats' field in info_dict is info_dict itself, |
b3d9ef88 JMF |
784 | # wich can't be exported to json |
785 | info_dict['formats'] = formats | |
bfaae0a7 | 786 | if self.params.get('listformats', None): |
787 | self.list_formats(info_dict) | |
788 | return | |
789 | ||
de3ef3ed | 790 | req_format = self.params.get('format') |
a9c58ad9 JMF |
791 | if req_format is None: |
792 | req_format = 'best' | |
dd82ffea | 793 | formats_to_download = [] |
dd82ffea | 794 | # The -1 is for supporting YoutubeIE |
a9c58ad9 | 795 | if req_format in ('-1', 'all'): |
dd82ffea JMF |
796 | formats_to_download = formats |
797 | else: | |
a9c5e5ca | 798 | # We can accept formats requested in the format: 34/5/best, we pick |
416a5efc | 799 | # the first that is available, starting from left |
dd82ffea JMF |
800 | req_formats = req_format.split('/') |
801 | for rf in req_formats: | |
6350728b JMF |
802 | if re.match(r'.+?\+.+?', rf) is not None: |
803 | # Two formats have been requested like '137+139' | |
804 | format_1, format_2 = rf.split('+') | |
805 | formats_info = (self.select_format(format_1, formats), | |
806 | self.select_format(format_2, formats)) | |
807 | if all(formats_info): | |
a9c5e5ca PH |
808 | selected_format = { |
809 | 'requested_formats': formats_info, | |
810 | 'format': rf, | |
811 | 'ext': formats_info[0]['ext'], | |
812 | } | |
6350728b JMF |
813 | else: |
814 | selected_format = None | |
815 | else: | |
816 | selected_format = self.select_format(rf, formats) | |
a9c58ad9 JMF |
817 | if selected_format is not None: |
818 | formats_to_download = [selected_format] | |
dd82ffea JMF |
819 | break |
820 | if not formats_to_download: | |
6febd1c1 | 821 | raise ExtractorError('requested format not available', |
78a3a9f8 | 822 | expected=True) |
dd82ffea JMF |
823 | |
824 | if download: | |
825 | if len(formats_to_download) > 1: | |
6febd1c1 | 826 | self.to_screen('[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) |
dd82ffea JMF |
827 | for format in formats_to_download: |
828 | new_info = dict(info_dict) | |
829 | new_info.update(format) | |
830 | self.process_info(new_info) | |
831 | # We update the info dict with the best quality format (backwards compatibility) | |
832 | info_dict.update(formats_to_download[-1]) | |
833 | return info_dict | |
834 | ||
8222d8de JMF |
835 | def process_info(self, info_dict): |
836 | """Process a single resolved IE result.""" | |
837 | ||
838 | assert info_dict.get('_type', 'video') == 'video' | |
fd288278 PH |
839 | |
840 | max_downloads = self.params.get('max_downloads') | |
841 | if max_downloads is not None: | |
842 | if self._num_downloads >= int(max_downloads): | |
843 | raise MaxDownloadsReached() | |
8222d8de JMF |
844 | |
845 | info_dict['fulltitle'] = info_dict['title'] | |
846 | if len(info_dict['title']) > 200: | |
6febd1c1 | 847 | info_dict['title'] = info_dict['title'][:197] + '...' |
8222d8de JMF |
848 | |
849 | # Keep for backwards compatibility | |
850 | info_dict['stitle'] = info_dict['title'] | |
851 | ||
852 | if not 'format' in info_dict: | |
853 | info_dict['format'] = info_dict['ext'] | |
854 | ||
855 | reason = self._match_entry(info_dict) | |
856 | if reason is not None: | |
6febd1c1 | 857 | self.to_screen('[download] ' + reason) |
8222d8de JMF |
858 | return |
859 | ||
fd288278 | 860 | self._num_downloads += 1 |
8222d8de JMF |
861 | |
862 | filename = self.prepare_filename(info_dict) | |
863 | ||
864 | # Forced printings | |
865 | if self.params.get('forcetitle', False): | |
0783b09b | 866 | self.to_stdout(info_dict['fulltitle']) |
8222d8de | 867 | if self.params.get('forceid', False): |
0783b09b | 868 | self.to_stdout(info_dict['id']) |
8222d8de | 869 | if self.params.get('forceurl', False): |
edde6c56 | 870 | # For RTMP URLs, also include the playpath |
6febd1c1 | 871 | self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) |
216d71d0 | 872 | if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: |
0783b09b | 873 | self.to_stdout(info_dict['thumbnail']) |
216d71d0 | 874 | if self.params.get('forcedescription', False) and info_dict.get('description') is not None: |
0783b09b | 875 | self.to_stdout(info_dict['description']) |
8222d8de | 876 | if self.params.get('forcefilename', False) and filename is not None: |
0783b09b | 877 | self.to_stdout(filename) |
525ef922 PH |
878 | if self.params.get('forceduration', False) and info_dict.get('duration') is not None: |
879 | self.to_stdout(formatSeconds(info_dict['duration'])) | |
8222d8de | 880 | if self.params.get('forceformat', False): |
0783b09b | 881 | self.to_stdout(info_dict['format']) |
9d153818 | 882 | if self.params.get('forcejson', False): |
a0d96c98 | 883 | info_dict['_filename'] = filename |
0783b09b | 884 | self.to_stdout(json.dumps(info_dict)) |
8222d8de JMF |
885 | |
886 | # Do nothing else if in simulate mode | |
887 | if self.params.get('simulate', False): | |
888 | return | |
889 | ||
890 | if filename is None: | |
891 | return | |
892 | ||
893 | try: | |
894 | dn = os.path.dirname(encodeFilename(filename)) | |
d26e981d | 895 | if dn and not os.path.exists(dn): |
8222d8de JMF |
896 | os.makedirs(dn) |
897 | except (OSError, IOError) as err: | |
6febd1c1 | 898 | self.report_error('unable to create directory ' + compat_str(err)) |
8222d8de JMF |
899 | return |
900 | ||
901 | if self.params.get('writedescription', False): | |
6febd1c1 | 902 | descfn = filename + '.description' |
7b6fefc9 | 903 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): |
6febd1c1 | 904 | self.to_screen('[info] Video description is already present') |
7b6fefc9 PH |
905 | else: |
906 | try: | |
6febd1c1 | 907 | self.to_screen('[info] Writing video description to: ' + descfn) |
7b6fefc9 PH |
908 | with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: |
909 | descfile.write(info_dict['description']) | |
910 | except (KeyError, TypeError): | |
6febd1c1 | 911 | self.report_warning('There\'s no description to write.') |
7b6fefc9 | 912 | except (OSError, IOError): |
6febd1c1 | 913 | self.report_error('Cannot write description file ' + descfn) |
7b6fefc9 | 914 | return |
8222d8de | 915 | |
1fb07d10 | 916 | if self.params.get('writeannotations', False): |
6febd1c1 | 917 | annofn = filename + '.annotations.xml' |
7b6fefc9 | 918 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): |
6febd1c1 | 919 | self.to_screen('[info] Video annotations are already present') |
7b6fefc9 PH |
920 | else: |
921 | try: | |
6febd1c1 | 922 | self.to_screen('[info] Writing video annotations to: ' + annofn) |
7b6fefc9 PH |
923 | with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: |
924 | annofile.write(info_dict['annotations']) | |
925 | except (KeyError, TypeError): | |
6febd1c1 | 926 | self.report_warning('There are no annotations to write.') |
7b6fefc9 | 927 | except (OSError, IOError): |
6febd1c1 | 928 | self.report_error('Cannot write annotations file: ' + annofn) |
7b6fefc9 | 929 | return |
1fb07d10 | 930 | |
c4a91be7 | 931 | subtitles_are_requested = any([self.params.get('writesubtitles', False), |
0b7f3118 | 932 | self.params.get('writeautomaticsub')]) |
c4a91be7 | 933 | |
fe7e0c98 | 934 | if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']: |
8222d8de JMF |
935 | # subtitles download errors are already managed as troubles in relevant IE |
936 | # that way it will silently go on when used with unsupporting IE | |
8222d8de | 937 | subtitles = info_dict['subtitles'] |
ca715127 | 938 | sub_format = self.params.get('subtitlesformat', 'srt') |
5d51a883 JMF |
939 | for sub_lang in subtitles.keys(): |
940 | sub = subtitles[sub_lang] | |
6804038d JMF |
941 | if sub is None: |
942 | continue | |
8222d8de | 943 | try: |
d4051a8e | 944 | sub_filename = subtitles_filename(filename, sub_lang, sub_format) |
7b6fefc9 | 945 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): |
6febd1c1 | 946 | self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) |
7b6fefc9 | 947 | else: |
6febd1c1 | 948 | self.to_screen('[info] Writing video subtitles to: ' + sub_filename) |
7b6fefc9 PH |
949 | with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: |
950 | subfile.write(sub) | |
8222d8de | 951 | except (OSError, IOError): |
e4db1951 | 952 | self.report_error('Cannot write subtitles file ' + sub_filename) |
8222d8de JMF |
953 | return |
954 | ||
8222d8de | 955 | if self.params.get('writeinfojson', False): |
6febd1c1 | 956 | infofn = os.path.splitext(filename)[0] + '.info.json' |
7b6fefc9 | 957 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)): |
6febd1c1 | 958 | self.to_screen('[info] Video description metadata is already present') |
7b6fefc9 | 959 | else: |
6febd1c1 | 960 | self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn) |
7b6fefc9 | 961 | try: |
1538eff6 | 962 | write_json_file(info_dict, encodeFilename(infofn)) |
7b6fefc9 | 963 | except (OSError, IOError): |
6febd1c1 | 964 | self.report_error('Cannot write metadata to JSON file ' + infofn) |
7b6fefc9 | 965 | return |
8222d8de JMF |
966 | |
967 | if self.params.get('writethumbnail', False): | |
d8269e1d | 968 | if info_dict.get('thumbnail') is not None: |
6febd1c1 PH |
969 | thumb_format = determine_ext(info_dict['thumbnail'], 'jpg') |
970 | thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format | |
0a9ce268 | 971 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)): |
6febd1c1 | 972 | self.to_screen('[%s] %s: Thumbnail is already present' % |
7b6fefc9 PH |
973 | (info_dict['extractor'], info_dict['id'])) |
974 | else: | |
6febd1c1 | 975 | self.to_screen('[%s] %s: Downloading thumbnail ...' % |
7b6fefc9 PH |
976 | (info_dict['extractor'], info_dict['id'])) |
977 | try: | |
e9c092f1 | 978 | uf = self.urlopen(info_dict['thumbnail']) |
7b6fefc9 PH |
979 | with open(thumb_filename, 'wb') as thumbf: |
980 | shutil.copyfileobj(uf, thumbf) | |
6febd1c1 | 981 | self.to_screen('[%s] %s: Writing thumbnail to: %s' % |
7b6fefc9 PH |
982 | (info_dict['extractor'], info_dict['id'], thumb_filename)) |
983 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
6febd1c1 | 984 | self.report_warning('Unable to download thumbnail "%s": %s' % |
7b6fefc9 | 985 | (info_dict['thumbnail'], compat_str(err))) |
8222d8de JMF |
986 | |
987 | if not self.params.get('skip_download', False): | |
988 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): | |
989 | success = True | |
990 | else: | |
991 | try: | |
6350728b JMF |
992 | def dl(name, info): |
993 | fd = get_suitable_downloader(info)(self, self.params) | |
994 | for ph in self._progress_hooks: | |
995 | fd.add_progress_hook(ph) | |
8d5797b0 PH |
996 | if self.params.get('verbose'): |
997 | self.to_stdout('[debug] Invoking downloader on %r' % info.get('url')) | |
6350728b JMF |
998 | return fd.download(name, info) |
999 | if info_dict.get('requested_formats') is not None: | |
1000 | downloaded = [] | |
1001 | success = True | |
58c3c7ae JMF |
1002 | merger = FFmpegMergerPP(self) |
1003 | if not merger._get_executable(): | |
1004 | postprocessors = [] | |
1005 | self.report_warning('You have requested multiple ' | |
1006 | 'formats but ffmpeg or avconv are not installed.' | |
1007 | ' The formats won\'t be merged') | |
1008 | else: | |
1009 | postprocessors = [merger] | |
6350728b JMF |
1010 | for f in info_dict['requested_formats']: |
1011 | new_info = dict(info_dict) | |
1012 | new_info.update(f) | |
1013 | fname = self.prepare_filename(new_info) | |
1014 | fname = prepend_extension(fname, 'f%s' % f['format_id']) | |
1015 | downloaded.append(fname) | |
1016 | partial_success = dl(fname, new_info) | |
1017 | success = success and partial_success | |
58c3c7ae | 1018 | info_dict['__postprocessors'] = postprocessors |
6350728b JMF |
1019 | info_dict['__files_to_merge'] = downloaded |
1020 | else: | |
1021 | # Just a single file | |
1022 | success = dl(filename, info_dict) | |
8222d8de | 1023 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
6febd1c1 | 1024 | self.report_error('unable to download video data: %s' % str(err)) |
8222d8de | 1025 | return |
c40c6aaa JMF |
1026 | except (OSError, IOError) as err: |
1027 | raise UnavailableVideoError(err) | |
8222d8de | 1028 | except (ContentTooShortError, ) as err: |
6febd1c1 | 1029 | self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) |
8222d8de JMF |
1030 | return |
1031 | ||
1032 | if success: | |
1033 | try: | |
1034 | self.post_process(filename, info_dict) | |
1035 | except (PostProcessingError) as err: | |
6febd1c1 | 1036 | self.report_error('postprocessing: %s' % str(err)) |
8222d8de JMF |
1037 | return |
1038 | ||
c1c9a79c PH |
1039 | self.record_download_archive(info_dict) |
1040 | ||
8222d8de JMF |
1041 | def download(self, url_list): |
1042 | """Download a given list of URLs.""" | |
acd69589 | 1043 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
0c75c3fa | 1044 | if (len(url_list) > 1 and |
acd69589 | 1045 | '%' not in outtmpl |
0c75c3fa | 1046 | and self.params.get('max_downloads') != 1): |
acd69589 | 1047 | raise SameFileError(outtmpl) |
8222d8de JMF |
1048 | |
1049 | for url in url_list: | |
1050 | try: | |
1051 | #It also downloads the videos | |
dca08720 | 1052 | self.extract_info(url) |
8222d8de | 1053 | except UnavailableVideoError: |
6febd1c1 | 1054 | self.report_error('unable to download video') |
8222d8de | 1055 | except MaxDownloadsReached: |
6febd1c1 | 1056 | self.to_screen('[info] Maximum number of downloaded files reached.') |
8222d8de JMF |
1057 | raise |
1058 | ||
1059 | return self._download_retcode | |
1060 | ||
1dcc4c0c | 1061 | def download_with_info_file(self, info_filename): |
395293a8 | 1062 | with io.open(info_filename, 'r', encoding='utf-8') as f: |
1dcc4c0c | 1063 | info = json.load(f) |
d4943898 JMF |
1064 | try: |
1065 | self.process_ie_result(info, download=True) | |
1066 | except DownloadError: | |
1067 | webpage_url = info.get('webpage_url') | |
1068 | if webpage_url is not None: | |
6febd1c1 | 1069 | self.report_warning('The info failed to download, trying with "%s"' % webpage_url) |
d4943898 JMF |
1070 | return self.download([webpage_url]) |
1071 | else: | |
1072 | raise | |
1073 | return self._download_retcode | |
1dcc4c0c | 1074 | |
8222d8de JMF |
1075 | def post_process(self, filename, ie_info): |
1076 | """Run all the postprocessors on the given file.""" | |
1077 | info = dict(ie_info) | |
1078 | info['filepath'] = filename | |
1079 | keep_video = None | |
6350728b JMF |
1080 | pps_chain = [] |
1081 | if ie_info.get('__postprocessors') is not None: | |
1082 | pps_chain.extend(ie_info['__postprocessors']) | |
1083 | pps_chain.extend(self._pps) | |
1084 | for pp in pps_chain: | |
8222d8de | 1085 | try: |
fe7e0c98 | 1086 | keep_video_wish, new_info = pp.run(info) |
8222d8de JMF |
1087 | if keep_video_wish is not None: |
1088 | if keep_video_wish: | |
1089 | keep_video = keep_video_wish | |
1090 | elif keep_video is None: | |
1091 | # No clear decision yet, let IE decide | |
1092 | keep_video = keep_video_wish | |
1093 | except PostProcessingError as e: | |
bbcbf4d4 | 1094 | self.report_error(e.msg) |
8222d8de JMF |
1095 | if keep_video is False and not self.params.get('keepvideo', False): |
1096 | try: | |
6febd1c1 | 1097 | self.to_screen('Deleting original file %s (pass -k to keep)' % filename) |
8222d8de JMF |
1098 | os.remove(encodeFilename(filename)) |
1099 | except (IOError, OSError): | |
6febd1c1 | 1100 | self.report_warning('Unable to remove downloaded video file') |
c1c9a79c | 1101 | |
5db07df6 PH |
1102 | def _make_archive_id(self, info_dict): |
1103 | # Future-proof against any change in case | |
1104 | # and backwards compatibility with prior versions | |
d31209a1 | 1105 | extractor = info_dict.get('extractor_key') |
7012b23c PH |
1106 | if extractor is None: |
1107 | if 'id' in info_dict: | |
1108 | extractor = info_dict.get('ie_key') # key in a playlist | |
1109 | if extractor is None: | |
5db07df6 | 1110 | return None # Incomplete video information |
6febd1c1 | 1111 | return extractor.lower() + ' ' + info_dict['id'] |
5db07df6 PH |
1112 | |
1113 | def in_download_archive(self, info_dict): | |
1114 | fn = self.params.get('download_archive') | |
1115 | if fn is None: | |
1116 | return False | |
1117 | ||
1118 | vid_id = self._make_archive_id(info_dict) | |
1119 | if vid_id is None: | |
7012b23c | 1120 | return False # Incomplete video information |
5db07df6 | 1121 | |
c1c9a79c PH |
1122 | try: |
1123 | with locked_file(fn, 'r', encoding='utf-8') as archive_file: | |
1124 | for line in archive_file: | |
1125 | if line.strip() == vid_id: | |
1126 | return True | |
1127 | except IOError as ioe: | |
1128 | if ioe.errno != errno.ENOENT: | |
1129 | raise | |
1130 | return False | |
1131 | ||
1132 | def record_download_archive(self, info_dict): | |
1133 | fn = self.params.get('download_archive') | |
1134 | if fn is None: | |
1135 | return | |
5db07df6 PH |
1136 | vid_id = self._make_archive_id(info_dict) |
1137 | assert vid_id | |
c1c9a79c | 1138 | with locked_file(fn, 'a', encoding='utf-8') as archive_file: |
6febd1c1 | 1139 | archive_file.write(vid_id + '\n') |
dd82ffea | 1140 | |
8c51aa65 | 1141 | @staticmethod |
8abeeb94 | 1142 | def format_resolution(format, default='unknown'): |
fb04e403 PH |
1143 | if format.get('vcodec') == 'none': |
1144 | return 'audio only' | |
f49d89ee PH |
1145 | if format.get('resolution') is not None: |
1146 | return format['resolution'] | |
8c51aa65 JMF |
1147 | if format.get('height') is not None: |
1148 | if format.get('width') is not None: | |
6febd1c1 | 1149 | res = '%sx%s' % (format['width'], format['height']) |
8c51aa65 | 1150 | else: |
6febd1c1 | 1151 | res = '%sp' % format['height'] |
f49d89ee | 1152 | elif format.get('width') is not None: |
6febd1c1 | 1153 | res = '?x%d' % format['width'] |
8c51aa65 | 1154 | else: |
8abeeb94 | 1155 | res = default |
8c51aa65 JMF |
1156 | return res |
1157 | ||
c57f7757 PH |
1158 | def _format_note(self, fdict): |
1159 | res = '' | |
1160 | if fdict.get('ext') in ['f4f', 'f4m']: | |
1161 | res += '(unsupported) ' | |
1162 | if fdict.get('format_note') is not None: | |
1163 | res += fdict['format_note'] + ' ' | |
1164 | if fdict.get('tbr') is not None: | |
1165 | res += '%4dk ' % fdict['tbr'] | |
1166 | if fdict.get('container') is not None: | |
1167 | if res: | |
1168 | res += ', ' | |
1169 | res += '%s container' % fdict['container'] | |
1170 | if (fdict.get('vcodec') is not None and | |
1171 | fdict.get('vcodec') != 'none'): | |
1172 | if res: | |
1173 | res += ', ' | |
1174 | res += fdict['vcodec'] | |
91c7271a | 1175 | if fdict.get('vbr') is not None: |
c57f7757 PH |
1176 | res += '@' |
1177 | elif fdict.get('vbr') is not None and fdict.get('abr') is not None: | |
1178 | res += 'video@' | |
1179 | if fdict.get('vbr') is not None: | |
1180 | res += '%4dk' % fdict['vbr'] | |
1181 | if fdict.get('acodec') is not None: | |
1182 | if res: | |
1183 | res += ', ' | |
1184 | if fdict['acodec'] == 'none': | |
1185 | res += 'video only' | |
1186 | else: | |
1187 | res += '%-5s' % fdict['acodec'] | |
1188 | elif fdict.get('abr') is not None: | |
1189 | if res: | |
1190 | res += ', ' | |
1191 | res += 'audio' | |
1192 | if fdict.get('abr') is not None: | |
1193 | res += '@%3dk' % fdict['abr'] | |
1194 | if fdict.get('asr') is not None: | |
1195 | res += ' (%5dHz)' % fdict['asr'] | |
1196 | if fdict.get('filesize') is not None: | |
1197 | if res: | |
1198 | res += ', ' | |
1199 | res += format_bytes(fdict['filesize']) | |
9732d77e PH |
1200 | elif fdict.get('filesize_approx') is not None: |
1201 | if res: | |
1202 | res += ', ' | |
1203 | res += '~' + format_bytes(fdict['filesize_approx']) | |
c57f7757 | 1204 | return res |
91c7271a | 1205 | |
c57f7757 | 1206 | def list_formats(self, info_dict): |
02dbf93f | 1207 | def line(format, idlen=20): |
6febd1c1 | 1208 | return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % ( |
8c51aa65 JMF |
1209 | format['format_id'], |
1210 | format['ext'], | |
8c51aa65 | 1211 | self.format_resolution(format), |
c57f7757 | 1212 | self._format_note(format), |
02dbf93f | 1213 | )) |
57dd9a8f | 1214 | |
94badb25 | 1215 | formats = info_dict.get('formats', [info_dict]) |
6febd1c1 | 1216 | idlen = max(len('format code'), |
02dbf93f PH |
1217 | max(len(f['format_id']) for f in formats)) |
1218 | formats_s = [line(f, idlen) for f in formats] | |
94badb25 | 1219 | if len(formats) > 1: |
c57f7757 PH |
1220 | formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)' |
1221 | formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)' | |
57dd9a8f PH |
1222 | |
1223 | header_line = line({ | |
6febd1c1 PH |
1224 | 'format_id': 'format code', 'ext': 'extension', |
1225 | 'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen) | |
1226 | self.to_screen('[info] Available formats for %s:\n%s\n%s' % | |
1227 | (info_dict['id'], header_line, '\n'.join(formats_s))) | |
dca08720 PH |
1228 | |
1229 | def urlopen(self, req): | |
1230 | """ Start an HTTP download """ | |
19a41fc6 | 1231 | return self._opener.open(req, timeout=self._socket_timeout) |
dca08720 PH |
1232 | |
1233 | def print_debug_header(self): | |
1234 | if not self.params.get('verbose'): | |
1235 | return | |
62fec3b2 | 1236 | |
b0472057 | 1237 | encoding_str = ( |
734f90bb PH |
1238 | '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( |
1239 | locale.getpreferredencoding(), | |
1240 | sys.getfilesystemencoding(), | |
1241 | sys.stdout.encoding, | |
b0472057 PH |
1242 | self.get_encoding())) |
1243 | try: | |
1244 | write_string(encoding_str, encoding=None) | |
1245 | except: | |
1246 | errmsg = 'Failed to write encoding string %r' % encoding_str | |
1247 | try: | |
1248 | sys.stdout.write(errmsg) | |
1249 | except: | |
1250 | pass | |
1251 | raise IOError(errmsg) | |
734f90bb PH |
1252 | |
1253 | self._write_string('[debug] youtube-dl version ' + __version__ + '\n') | |
dca08720 PH |
1254 | try: |
1255 | sp = subprocess.Popen( | |
1256 | ['git', 'rev-parse', '--short', 'HEAD'], | |
1257 | stdout=subprocess.PIPE, stderr=subprocess.PIPE, | |
1258 | cwd=os.path.dirname(os.path.abspath(__file__))) | |
1259 | out, err = sp.communicate() | |
1260 | out = out.decode().strip() | |
1261 | if re.match('[0-9a-f]+', out): | |
734f90bb | 1262 | self._write_string('[debug] Git HEAD: ' + out + '\n') |
dca08720 PH |
1263 | except: |
1264 | try: | |
1265 | sys.exc_clear() | |
1266 | except: | |
1267 | pass | |
734f90bb | 1268 | self._write_string('[debug] Python version %s - %s' % |
6febd1c1 | 1269 | (platform.python_version(), platform_name()) + '\n') |
dca08720 PH |
1270 | |
1271 | proxy_map = {} | |
1272 | for handler in self._opener.handlers: | |
1273 | if hasattr(handler, 'proxies'): | |
1274 | proxy_map.update(handler.proxies) | |
734f90bb | 1275 | self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') |
dca08720 | 1276 | |
e344693b | 1277 | def _setup_opener(self): |
6ad14cab | 1278 | timeout_val = self.params.get('socket_timeout') |
19a41fc6 | 1279 | self._socket_timeout = 600 if timeout_val is None else float(timeout_val) |
6ad14cab | 1280 | |
dca08720 PH |
1281 | opts_cookiefile = self.params.get('cookiefile') |
1282 | opts_proxy = self.params.get('proxy') | |
1283 | ||
1284 | if opts_cookiefile is None: | |
1285 | self.cookiejar = compat_cookiejar.CookieJar() | |
1286 | else: | |
1287 | self.cookiejar = compat_cookiejar.MozillaCookieJar( | |
1288 | opts_cookiefile) | |
1289 | if os.access(opts_cookiefile, os.R_OK): | |
1290 | self.cookiejar.load() | |
1291 | ||
1292 | cookie_processor = compat_urllib_request.HTTPCookieProcessor( | |
1293 | self.cookiejar) | |
1294 | if opts_proxy is not None: | |
1295 | if opts_proxy == '': | |
1296 | proxies = {} | |
1297 | else: | |
1298 | proxies = {'http': opts_proxy, 'https': opts_proxy} | |
1299 | else: | |
1300 | proxies = compat_urllib_request.getproxies() | |
1301 | # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) | |
1302 | if 'http' in proxies and 'https' not in proxies: | |
1303 | proxies['https'] = proxies['http'] | |
1304 | proxy_handler = compat_urllib_request.ProxyHandler(proxies) | |
a0ddb8a2 PH |
1305 | |
1306 | debuglevel = 1 if self.params.get('debug_printtraffic') else 0 | |
dca08720 | 1307 | https_handler = make_HTTPS_handler( |
a0ddb8a2 PH |
1308 | self.params.get('nocheckcertificate', False), debuglevel=debuglevel) |
1309 | ydlh = YoutubeDLHandler(debuglevel=debuglevel) | |
dca08720 | 1310 | opener = compat_urllib_request.build_opener( |
a0ddb8a2 | 1311 | https_handler, proxy_handler, cookie_processor, ydlh) |
dca08720 PH |
1312 | # Delete the default user-agent header, which would otherwise apply in |
1313 | # cases where our custom HTTP handler doesn't come into play | |
1314 | # (See https://github.com/rg3/youtube-dl/issues/1309 for details) | |
1315 | opener.addheaders = [] | |
1316 | self._opener = opener | |
62fec3b2 PH |
1317 | |
1318 | def encode(self, s): | |
1319 | if isinstance(s, bytes): | |
1320 | return s # Already encoded | |
1321 | ||
1322 | try: | |
1323 | return s.encode(self.get_encoding()) | |
1324 | except UnicodeEncodeError as err: | |
1325 | err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.' | |
1326 | raise | |
1327 | ||
1328 | def get_encoding(self): | |
1329 | encoding = self.params.get('encoding') | |
1330 | if encoding is None: | |
1331 | encoding = preferredencoding() | |
1332 | return encoding |