]>
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 |
31bd3925 | 7 | import contextlib |
9d2ecdbc | 8 | import datetime |
c1c9a79c | 9 | import errno |
31bd3925 | 10 | import fileinput |
8222d8de | 11 | import io |
b82f815f | 12 | import itertools |
8694c600 | 13 | import json |
62fec3b2 | 14 | import locale |
083c9df9 | 15 | import operator |
8222d8de | 16 | import os |
dca08720 | 17 | import platform |
8222d8de JMF |
18 | import re |
19 | import shutil | |
dca08720 | 20 | import subprocess |
8222d8de JMF |
21 | import socket |
22 | import sys | |
23 | import time | |
24 | import traceback | |
25 | ||
1e5b9a95 PH |
26 | if os.name == 'nt': |
27 | import ctypes | |
28 | ||
8c25f81b | 29 | from .compat import ( |
8f9312c3 | 30 | compat_basestring, |
dca08720 | 31 | compat_cookiejar, |
4644ac55 | 32 | compat_expanduser, |
003c69a8 | 33 | compat_get_terminal_size, |
ce02ed60 | 34 | compat_http_client, |
4f026faf | 35 | compat_kwargs, |
ce02ed60 PH |
36 | compat_str, |
37 | compat_urllib_error, | |
38 | compat_urllib_request, | |
8c25f81b PH |
39 | ) |
40 | from .utils import ( | |
d05cfe06 | 41 | escape_url, |
ce02ed60 PH |
42 | ContentTooShortError, |
43 | date_from_str, | |
44 | DateRange, | |
acd69589 | 45 | DEFAULT_OUTTMPL, |
ce02ed60 PH |
46 | determine_ext, |
47 | DownloadError, | |
48 | encodeFilename, | |
49 | ExtractorError, | |
02dbf93f | 50 | format_bytes, |
525ef922 | 51 | formatSeconds, |
ce02ed60 | 52 | locked_file, |
dca08720 | 53 | make_HTTPS_handler, |
ce02ed60 | 54 | MaxDownloadsReached, |
b7ab0590 | 55 | PagedList, |
083c9df9 | 56 | parse_filesize, |
91410c9b | 57 | PerRequestProxyHandler, |
ce02ed60 | 58 | PostProcessingError, |
dca08720 | 59 | platform_name, |
ce02ed60 | 60 | preferredencoding, |
cfb56d1a | 61 | render_table, |
ce02ed60 PH |
62 | SameFileError, |
63 | sanitize_filename, | |
1bb5c511 | 64 | sanitize_path, |
e5660ee6 | 65 | std_headers, |
ce02ed60 PH |
66 | subtitles_filename, |
67 | takewhile_inclusive, | |
68 | UnavailableVideoError, | |
29eb5174 | 69 | url_basename, |
58b1f00d | 70 | version_tuple, |
ce02ed60 PH |
71 | write_json_file, |
72 | write_string, | |
dca08720 | 73 | YoutubeDLHandler, |
6350728b | 74 | prepend_extension, |
7d4111ed | 75 | args_to_str, |
05900629 | 76 | age_restricted, |
ce02ed60 | 77 | ) |
a0e07d31 | 78 | from .cache import Cache |
023fa8c4 | 79 | from .extractor import get_info_extractor, gen_extractors |
3bc2ddcc | 80 | from .downloader import get_suitable_downloader |
4c83c967 | 81 | from .downloader.rtmp import rtmpdump_version |
4f026faf | 82 | from .postprocessor import ( |
62cd676c | 83 | FFmpegFixupM4aPP, |
6271f1ca | 84 | FFmpegFixupStretchedPP, |
4f026faf PH |
85 | FFmpegMergerPP, |
86 | FFmpegPostProcessor, | |
87 | get_postprocessor, | |
88 | ) | |
dca08720 | 89 | from .version import __version__ |
8222d8de JMF |
90 | |
91 | ||
92 | class YoutubeDL(object): | |
93 | """YoutubeDL class. | |
94 | ||
95 | YoutubeDL objects are the ones responsible of downloading the | |
96 | actual video file and writing it to disk if the user has requested | |
97 | it, among some other tasks. In most cases there should be one per | |
98 | program. As, given a video URL, the downloader doesn't know how to | |
99 | extract all the needed information, task that InfoExtractors do, it | |
100 | has to pass the URL to one of them. | |
101 | ||
102 | For this, YoutubeDL objects have a method that allows | |
103 | InfoExtractors to be registered in a given order. When it is passed | |
104 | a URL, the YoutubeDL object handles it to the first InfoExtractor it | |
105 | finds that reports being able to handle it. The InfoExtractor extracts | |
106 | all the information about the video or videos the URL refers to, and | |
107 | YoutubeDL process the extracted information, possibly using a File | |
108 | Downloader to download the video. | |
109 | ||
110 | YoutubeDL objects accept a lot of parameters. In order not to saturate | |
111 | the object constructor with arguments, it receives a dictionary of | |
112 | options instead. These options are available through the params | |
113 | attribute for the InfoExtractors to use. The YoutubeDL also | |
114 | registers itself as the downloader in charge for the InfoExtractors | |
115 | that are added to it, so this is a "mutual registration". | |
116 | ||
117 | Available options: | |
118 | ||
119 | username: Username for authentication purposes. | |
120 | password: Password for authentication purposes. | |
c6c19746 | 121 | videopassword: Password for acces a video. |
8222d8de JMF |
122 | usenetrc: Use netrc for authentication instead. |
123 | verbose: Print additional info to stdout. | |
124 | quiet: Do not print messages to stdout. | |
ad8915b7 | 125 | no_warnings: Do not print out anything for warnings. |
8222d8de JMF |
126 | forceurl: Force printing final URL. |
127 | forcetitle: Force printing title. | |
128 | forceid: Force printing ID. | |
129 | forcethumbnail: Force printing thumbnail URL. | |
130 | forcedescription: Force printing description. | |
131 | forcefilename: Force printing final filename. | |
525ef922 | 132 | forceduration: Force printing duration. |
8694c600 | 133 | forcejson: Force printing info_dict as JSON. |
63e0be34 PH |
134 | dump_single_json: Force printing the info_dict of the whole playlist |
135 | (or video) as a single JSON line. | |
8222d8de | 136 | simulate: Do not download the video files. |
d8600787 | 137 | format: Video format code. See options.py for more information. |
8222d8de JMF |
138 | format_limit: Highest quality format to try. |
139 | outtmpl: Template for output names. | |
140 | restrictfilenames: Do not allow "&" and spaces in file names | |
141 | ignoreerrors: Do not stop on download errors. | |
142 | nooverwrites: Prevent overwriting files. | |
143 | playliststart: Playlist item to start at. | |
144 | playlistend: Playlist item to end at. | |
c14e88f0 | 145 | playlist_items: Specific indices of playlist to download. |
ff815fe6 | 146 | playlistreverse: Download playlist items in reverse order. |
8222d8de JMF |
147 | matchtitle: Download only matching titles. |
148 | rejecttitle: Reject downloads for matching titles. | |
8bf9319e | 149 | logger: Log messages to a logging.Logger instance. |
8222d8de JMF |
150 | logtostderr: Log messages to stderr instead of stdout. |
151 | writedescription: Write the video description to a .description file | |
152 | writeinfojson: Write the video description to a .info.json file | |
1fb07d10 | 153 | writeannotations: Write the video annotations to a .annotations.xml file |
8222d8de | 154 | writethumbnail: Write the thumbnail image to a file |
ec82d85a | 155 | write_all_thumbnails: Write all thumbnail formats to files |
8222d8de | 156 | writesubtitles: Write the video subtitles to a file |
b004821f | 157 | writeautomaticsub: Write the automatic subtitles to a file |
8222d8de | 158 | allsubtitles: Downloads all the subtitles of the video |
0b7f3118 | 159 | (requires writesubtitles or writeautomaticsub) |
8222d8de | 160 | listsubtitles: Lists all available subtitles for the video |
a504ced0 | 161 | subtitlesformat: The format code for subtitles |
aa6a10c4 | 162 | subtitleslangs: List of languages of the subtitles to download |
8222d8de JMF |
163 | keepvideo: Keep the video file after post-processing |
164 | daterange: A DateRange object, download only if the upload_date is in the range. | |
165 | skip_download: Skip the actual download of the video file | |
c35f9e72 | 166 | cachedir: Location of the cache files in the filesystem. |
a0e07d31 | 167 | False to disable filesystem cache. |
47192f92 | 168 | noplaylist: Download single video instead of a playlist if in doubt. |
8dbe9899 PH |
169 | age_limit: An integer representing the user's age in years. |
170 | Unsuitable videos for the given age are skipped. | |
5fe18bdb PH |
171 | min_views: An integer representing the minimum view count the video |
172 | must have in order to not be skipped. | |
173 | Videos without view count information are always | |
174 | downloaded. None for no limit. | |
175 | max_views: An integer representing the maximum view count. | |
176 | Videos that are more popular than that are not | |
177 | downloaded. | |
178 | Videos without view count information are always | |
179 | downloaded. None for no limit. | |
180 | download_archive: File name of a file where all downloads are recorded. | |
c1c9a79c PH |
181 | Videos already present in the file are not downloaded |
182 | again. | |
dca08720 | 183 | cookiefile: File name where cookies should be read from and dumped to. |
a1ee09e8 | 184 | nocheckcertificate:Do not verify SSL certificates |
7e8c0af0 PH |
185 | prefer_insecure: Use HTTP instead of HTTPS to retrieve information. |
186 | At the moment, this is only supported by YouTube. | |
a1ee09e8 | 187 | proxy: URL of the proxy server to use |
91410c9b PH |
188 | cn_verification_proxy: URL of the proxy to use for IP address verification |
189 | on Chinese sites. (Experimental) | |
e344693b | 190 | socket_timeout: Time to wait for unresponsive hosts, in seconds |
0783b09b PH |
191 | bidi_workaround: Work around buggy terminals without bidirectional text |
192 | support, using fridibi | |
a0ddb8a2 | 193 | debug_printtraffic:Print out sent and received HTTP traffic |
7b0817e8 | 194 | include_ads: Download ads as well |
04b4d394 PH |
195 | default_search: Prepend this string if an input url is not valid. |
196 | 'auto' for elaborate guessing | |
62fec3b2 | 197 | encoding: Use this encoding instead of the system-specified. |
e8ee972c | 198 | extract_flat: Do not resolve URLs, return the immediate result. |
057a5206 PH |
199 | Pass in 'in_playlist' to only show this behavior for |
200 | playlist items. | |
4f026faf | 201 | postprocessors: A list of dictionaries, each with an entry |
71b640cc PH |
202 | * key: The name of the postprocessor. See |
203 | youtube_dl/postprocessor/__init__.py for a list. | |
4f026faf PH |
204 | as well as any further keyword arguments for the |
205 | postprocessor. | |
71b640cc PH |
206 | progress_hooks: A list of functions that get called on download |
207 | progress, with a dictionary with the entries | |
5cda4eda | 208 | * status: One of "downloading", "error", or "finished". |
ee69b99a | 209 | Check this first and ignore unknown values. |
71b640cc | 210 | |
5cda4eda | 211 | If status is one of "downloading", or "finished", the |
ee69b99a PH |
212 | following properties may also be present: |
213 | * filename: The final filename (always present) | |
5cda4eda | 214 | * tmpfilename: The filename we're currently writing to |
71b640cc PH |
215 | * downloaded_bytes: Bytes on disk |
216 | * total_bytes: Size of the whole file, None if unknown | |
5cda4eda PH |
217 | * total_bytes_estimate: Guess of the eventual file size, |
218 | None if unavailable. | |
219 | * elapsed: The number of seconds since download started. | |
71b640cc PH |
220 | * eta: The estimated time in seconds, None if unknown |
221 | * speed: The download speed in bytes/second, None if | |
222 | unknown | |
5cda4eda PH |
223 | * fragment_index: The counter of the currently |
224 | downloaded video fragment. | |
225 | * fragment_count: The number of fragments (= individual | |
226 | files that will be merged) | |
71b640cc PH |
227 | |
228 | Progress hooks are guaranteed to be called at least once | |
229 | (with status "finished") if the download is successful. | |
45598f15 | 230 | merge_output_format: Extension to use when merging formats. |
6271f1ca PH |
231 | fixup: Automatically correct known faults of the file. |
232 | One of: | |
233 | - "never": do nothing | |
234 | - "warn": only emit a warning | |
235 | - "detect_or_warn": check whether we can do anything | |
62cd676c | 236 | about it, warn otherwise (default) |
be4a824d | 237 | source_address: (Experimental) Client-side IP address to bind to. |
8bfa7545 PH |
238 | call_home: Boolean, true iff we are allowed to contact the |
239 | youtube-dl servers for debugging. | |
5f0d813d | 240 | sleep_interval: Number of seconds to sleep before each download. |
cfb56d1a PH |
241 | listformats: Print an overview of available video formats and exit. |
242 | list_thumbnails: Print a table of all thumbnails and exit. | |
347de493 PH |
243 | match_filter: A function that gets called with the info_dict of |
244 | every video. | |
245 | If it returns a message, the video is ignored. | |
246 | If it returns None, the video is downloaded. | |
247 | match_filter_func in utils.py is one example for this. | |
7e5db8c9 | 248 | no_color: Do not emit color codes in output. |
71b640cc | 249 | |
85729c51 PH |
250 | The following options determine which downloader is picked: |
251 | external_downloader: Executable of the external downloader to call. | |
252 | None or unset for standard (built-in) downloader. | |
253 | hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv. | |
fe7e0c98 | 254 | |
8222d8de | 255 | The following parameters are not used by YoutubeDL itself, they are used by |
c75f0b36 | 256 | the downloader (see youtube_dl/downloader/common.py): |
8222d8de | 257 | nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, |
881e6a1f | 258 | noresizebuffer, retries, continuedl, noprogress, consoletitle, |
c75f0b36 | 259 | xattr_set_filesize, external_downloader_args. |
76b1bd67 JMF |
260 | |
261 | The following options are used by the post processors: | |
262 | prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, | |
263 | otherwise prefer avconv. | |
8d31fa3c | 264 | exec_cmd: Arbitrary command to run after downloading |
8222d8de JMF |
265 | """ |
266 | ||
267 | params = None | |
268 | _ies = [] | |
269 | _pps = [] | |
270 | _download_retcode = None | |
271 | _num_downloads = None | |
272 | _screen_file = None | |
273 | ||
3511266b | 274 | def __init__(self, params=None, auto_init=True): |
8222d8de | 275 | """Create a FileDownloader object with the given options.""" |
e9f9a10f JMF |
276 | if params is None: |
277 | params = {} | |
8222d8de | 278 | self._ies = [] |
56c73665 | 279 | self._ies_instances = {} |
8222d8de | 280 | self._pps = [] |
933605d7 | 281 | self._progress_hooks = [] |
8222d8de JMF |
282 | self._download_retcode = 0 |
283 | self._num_downloads = 0 | |
284 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] | |
0783b09b | 285 | self._err_file = sys.stderr |
e9f9a10f | 286 | self.params = params |
a0e07d31 | 287 | self.cache = Cache(self) |
34308b30 | 288 | |
0783b09b | 289 | if params.get('bidi_workaround', False): |
1c088fa8 PH |
290 | try: |
291 | import pty | |
292 | master, slave = pty.openpty() | |
003c69a8 | 293 | width = compat_get_terminal_size().columns |
1c088fa8 PH |
294 | if width is None: |
295 | width_args = [] | |
296 | else: | |
297 | width_args = ['-w', str(width)] | |
5d681e96 | 298 | sp_kwargs = dict( |
1c088fa8 PH |
299 | stdin=subprocess.PIPE, |
300 | stdout=slave, | |
301 | stderr=self._err_file) | |
5d681e96 PH |
302 | try: |
303 | self._output_process = subprocess.Popen( | |
304 | ['bidiv'] + width_args, **sp_kwargs | |
305 | ) | |
306 | except OSError: | |
5d681e96 PH |
307 | self._output_process = subprocess.Popen( |
308 | ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) | |
309 | self._output_channel = os.fdopen(master, 'rb') | |
1c088fa8 PH |
310 | except OSError as ose: |
311 | if ose.errno == 2: | |
6febd1c1 | 312 | 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 $PATH.') |
1c088fa8 PH |
313 | else: |
314 | raise | |
0783b09b | 315 | |
34308b30 | 316 | if (sys.version_info >= (3,) and sys.platform != 'win32' and |
8fb3ac36 PH |
317 | sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and |
318 | not params.get('restrictfilenames', False)): | |
34308b30 PH |
319 | # On Python 3, the Unicode filesystem API will throw errors (#1474) |
320 | self.report_warning( | |
6febd1c1 | 321 | 'Assuming --restrict-filenames since file system encoding ' |
1b725173 | 322 | 'cannot encode all characters. ' |
6febd1c1 | 323 | 'Set the LC_ALL environment variable to fix this.') |
4a98cdbf | 324 | self.params['restrictfilenames'] = True |
34308b30 | 325 | |
486dd09e PH |
326 | if isinstance(params.get('outtmpl'), bytes): |
327 | self.report_warning( | |
328 | 'Parameter outtmpl is bytes, but should be a unicode string. ' | |
329 | 'Put from __future__ import unicode_literals at the top of your code file or consider switching to Python 3.x.') | |
330 | ||
dca08720 PH |
331 | self._setup_opener() |
332 | ||
3511266b PH |
333 | if auto_init: |
334 | self.print_debug_header() | |
335 | self.add_default_info_extractors() | |
336 | ||
4f026faf PH |
337 | for pp_def_raw in self.params.get('postprocessors', []): |
338 | pp_class = get_postprocessor(pp_def_raw['key']) | |
339 | pp_def = dict(pp_def_raw) | |
340 | del pp_def['key'] | |
341 | pp = pp_class(self, **compat_kwargs(pp_def)) | |
342 | self.add_post_processor(pp) | |
343 | ||
71b640cc PH |
344 | for ph in self.params.get('progress_hooks', []): |
345 | self.add_progress_hook(ph) | |
346 | ||
7d4111ed PH |
347 | def warn_if_short_id(self, argv): |
348 | # short YouTube ID starting with dash? | |
349 | idxs = [ | |
350 | i for i, a in enumerate(argv) | |
351 | if re.match(r'^-[0-9A-Za-z_-]{10}$', a)] | |
352 | if idxs: | |
353 | correct_argv = ( | |
354 | ['youtube-dl'] + | |
355 | [a for i, a in enumerate(argv) if i not in idxs] + | |
356 | ['--'] + [argv[i] for i in idxs] | |
357 | ) | |
358 | self.report_warning( | |
359 | 'Long argument string detected. ' | |
360 | 'Use -- to separate parameters and URLs, like this:\n%s\n' % | |
361 | args_to_str(correct_argv)) | |
362 | ||
8222d8de JMF |
363 | def add_info_extractor(self, ie): |
364 | """Add an InfoExtractor object to the end of the list.""" | |
365 | self._ies.append(ie) | |
56c73665 | 366 | self._ies_instances[ie.ie_key()] = ie |
8222d8de JMF |
367 | ie.set_downloader(self) |
368 | ||
56c73665 JMF |
369 | def get_info_extractor(self, ie_key): |
370 | """ | |
371 | Get an instance of an IE with name ie_key, it will try to get one from | |
372 | the _ies list, if there's no instance it will create a new one and add | |
373 | it to the extractor list. | |
374 | """ | |
375 | ie = self._ies_instances.get(ie_key) | |
376 | if ie is None: | |
377 | ie = get_info_extractor(ie_key)() | |
378 | self.add_info_extractor(ie) | |
379 | return ie | |
380 | ||
023fa8c4 JMF |
381 | def add_default_info_extractors(self): |
382 | """ | |
383 | Add the InfoExtractors returned by gen_extractors to the end of the list | |
384 | """ | |
385 | for ie in gen_extractors(): | |
386 | self.add_info_extractor(ie) | |
387 | ||
8222d8de JMF |
388 | def add_post_processor(self, pp): |
389 | """Add a PostProcessor object to the end of the chain.""" | |
390 | self._pps.append(pp) | |
391 | pp.set_downloader(self) | |
392 | ||
933605d7 JMF |
393 | def add_progress_hook(self, ph): |
394 | """Add the progress hook (currently only for the file downloader)""" | |
395 | self._progress_hooks.append(ph) | |
8ab470f1 | 396 | |
1c088fa8 | 397 | def _bidi_workaround(self, message): |
5d681e96 | 398 | if not hasattr(self, '_output_channel'): |
1c088fa8 PH |
399 | return message |
400 | ||
5d681e96 | 401 | assert hasattr(self, '_output_process') |
11b85ce6 | 402 | assert isinstance(message, compat_str) |
6febd1c1 PH |
403 | line_count = message.count('\n') + 1 |
404 | self._output_process.stdin.write((message + '\n').encode('utf-8')) | |
5d681e96 | 405 | self._output_process.stdin.flush() |
6febd1c1 | 406 | res = ''.join(self._output_channel.readline().decode('utf-8') |
9e1a5b84 | 407 | for _ in range(line_count)) |
6febd1c1 | 408 | return res[:-len('\n')] |
1c088fa8 | 409 | |
8222d8de | 410 | def to_screen(self, message, skip_eol=False): |
0783b09b PH |
411 | """Print message to stdout if not in quiet mode.""" |
412 | return self.to_stdout(message, skip_eol, check_quiet=True) | |
413 | ||
734f90bb | 414 | def _write_string(self, s, out=None): |
b58ddb32 | 415 | write_string(s, out=out, encoding=self.params.get('encoding')) |
734f90bb | 416 | |
0783b09b | 417 | def to_stdout(self, message, skip_eol=False, check_quiet=False): |
8222d8de | 418 | """Print message to stdout if not in quiet mode.""" |
8bf9319e | 419 | if self.params.get('logger'): |
43afe285 | 420 | self.params['logger'].debug(message) |
0783b09b | 421 | elif not check_quiet or not self.params.get('quiet', False): |
1c088fa8 | 422 | message = self._bidi_workaround(message) |
6febd1c1 | 423 | terminator = ['\n', ''][skip_eol] |
8222d8de | 424 | output = message + terminator |
1c088fa8 | 425 | |
734f90bb | 426 | self._write_string(output, self._screen_file) |
8222d8de JMF |
427 | |
428 | def to_stderr(self, message): | |
429 | """Print message to stderr.""" | |
11b85ce6 | 430 | assert isinstance(message, compat_str) |
8bf9319e | 431 | if self.params.get('logger'): |
43afe285 IB |
432 | self.params['logger'].error(message) |
433 | else: | |
1c088fa8 | 434 | message = self._bidi_workaround(message) |
6febd1c1 | 435 | output = message + '\n' |
734f90bb | 436 | self._write_string(output, self._err_file) |
8222d8de | 437 | |
1e5b9a95 PH |
438 | def to_console_title(self, message): |
439 | if not self.params.get('consoletitle', False): | |
440 | return | |
441 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
442 | # c_wchar_p() might not be necessary if `message` is | |
443 | # already of type unicode() | |
444 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
445 | elif 'TERM' in os.environ: | |
734f90bb | 446 | self._write_string('\033]0;%s\007' % message, self._screen_file) |
1e5b9a95 | 447 | |
bdde425c PH |
448 | def save_console_title(self): |
449 | if not self.params.get('consoletitle', False): | |
450 | return | |
451 | if 'TERM' in os.environ: | |
efd6c574 | 452 | # Save the title on stack |
734f90bb | 453 | self._write_string('\033[22;0t', self._screen_file) |
bdde425c PH |
454 | |
455 | def restore_console_title(self): | |
456 | if not self.params.get('consoletitle', False): | |
457 | return | |
458 | if 'TERM' in os.environ: | |
efd6c574 | 459 | # Restore the title from stack |
734f90bb | 460 | self._write_string('\033[23;0t', self._screen_file) |
bdde425c PH |
461 | |
462 | def __enter__(self): | |
463 | self.save_console_title() | |
464 | return self | |
465 | ||
466 | def __exit__(self, *args): | |
467 | self.restore_console_title() | |
f89197d7 | 468 | |
dca08720 PH |
469 | if self.params.get('cookiefile') is not None: |
470 | self.cookiejar.save() | |
bdde425c | 471 | |
8222d8de JMF |
472 | def trouble(self, message=None, tb=None): |
473 | """Determine action to take when a download problem appears. | |
474 | ||
475 | Depending on if the downloader has been configured to ignore | |
476 | download errors or not, this method may throw an exception or | |
477 | not when errors are found, after printing the message. | |
478 | ||
479 | tb, if given, is additional traceback information. | |
480 | """ | |
481 | if message is not None: | |
482 | self.to_stderr(message) | |
483 | if self.params.get('verbose'): | |
484 | if tb is None: | |
485 | if sys.exc_info()[0]: # if .trouble has been called from an except block | |
6febd1c1 | 486 | tb = '' |
8222d8de | 487 | if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: |
6febd1c1 | 488 | tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) |
8222d8de JMF |
489 | tb += compat_str(traceback.format_exc()) |
490 | else: | |
491 | tb_data = traceback.format_list(traceback.extract_stack()) | |
6febd1c1 | 492 | tb = ''.join(tb_data) |
8222d8de JMF |
493 | self.to_stderr(tb) |
494 | if not self.params.get('ignoreerrors', False): | |
495 | if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: | |
496 | exc_info = sys.exc_info()[1].exc_info | |
497 | else: | |
498 | exc_info = sys.exc_info() | |
499 | raise DownloadError(message, exc_info) | |
500 | self._download_retcode = 1 | |
501 | ||
502 | def report_warning(self, message): | |
503 | ''' | |
504 | Print the message to stderr, it will be prefixed with 'WARNING:' | |
505 | If stderr is a tty file the 'WARNING:' will be colored | |
506 | ''' | |
6d07ce01 JMF |
507 | if self.params.get('logger') is not None: |
508 | self.params['logger'].warning(message) | |
8222d8de | 509 | else: |
ad8915b7 PH |
510 | if self.params.get('no_warnings'): |
511 | return | |
7e5db8c9 | 512 | if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt': |
6d07ce01 JMF |
513 | _msg_header = '\033[0;33mWARNING:\033[0m' |
514 | else: | |
515 | _msg_header = 'WARNING:' | |
516 | warning_message = '%s %s' % (_msg_header, message) | |
517 | self.to_stderr(warning_message) | |
8222d8de JMF |
518 | |
519 | def report_error(self, message, tb=None): | |
520 | ''' | |
521 | Do the same as trouble, but prefixes the message with 'ERROR:', colored | |
522 | in red if stderr is a tty file. | |
523 | ''' | |
7e5db8c9 | 524 | if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt': |
6febd1c1 | 525 | _msg_header = '\033[0;31mERROR:\033[0m' |
8222d8de | 526 | else: |
6febd1c1 PH |
527 | _msg_header = 'ERROR:' |
528 | error_message = '%s %s' % (_msg_header, message) | |
8222d8de JMF |
529 | self.trouble(error_message, tb) |
530 | ||
8222d8de JMF |
531 | def report_file_already_downloaded(self, file_name): |
532 | """Report file has already been fully downloaded.""" | |
533 | try: | |
6febd1c1 | 534 | self.to_screen('[download] %s has already been downloaded' % file_name) |
ce02ed60 | 535 | except UnicodeEncodeError: |
6febd1c1 | 536 | self.to_screen('[download] The file has already been downloaded') |
8222d8de | 537 | |
8222d8de JMF |
538 | def prepare_filename(self, info_dict): |
539 | """Generate the output filename.""" | |
540 | try: | |
541 | template_dict = dict(info_dict) | |
542 | ||
543 | template_dict['epoch'] = int(time.time()) | |
544 | autonumber_size = self.params.get('autonumber_size') | |
545 | if autonumber_size is None: | |
546 | autonumber_size = 5 | |
6febd1c1 | 547 | autonumber_templ = '%0' + str(autonumber_size) + 'd' |
8222d8de | 548 | template_dict['autonumber'] = autonumber_templ % self._num_downloads |
702665c0 | 549 | if template_dict.get('playlist_index') is not None: |
c6b4132a | 550 | template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index']) |
17b75c0d PH |
551 | if template_dict.get('resolution') is None: |
552 | if template_dict.get('width') and template_dict.get('height'): | |
553 | template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height']) | |
554 | elif template_dict.get('height'): | |
805ef3c6 | 555 | template_dict['resolution'] = '%sp' % template_dict['height'] |
17b75c0d | 556 | elif template_dict.get('width'): |
805ef3c6 | 557 | template_dict['resolution'] = '?x%d' % template_dict['width'] |
8222d8de | 558 | |
586a91b6 | 559 | sanitize = lambda k, v: sanitize_filename( |
45598aab | 560 | compat_str(v), |
1bb5c511 | 561 | restricted=self.params.get('restrictfilenames'), |
6febd1c1 | 562 | is_id=(k == 'id')) |
586a91b6 | 563 | template_dict = dict((k, sanitize(k, v)) |
45598aab PH |
564 | for k, v in template_dict.items() |
565 | if v is not None) | |
6febd1c1 | 566 | template_dict = collections.defaultdict(lambda: 'NA', template_dict) |
8222d8de | 567 | |
1bb5c511 | 568 | outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL)) |
4644ac55 | 569 | tmpl = compat_expanduser(outtmpl) |
586a91b6 | 570 | filename = tmpl % template_dict |
3a0d2f52 S |
571 | # Temporary fix for #4787 |
572 | # 'Treat' all problem characters by passing filename through preferredencoding | |
573 | # to workaround encoding issues with subprocess on python2 @ Windows | |
574 | if sys.version_info < (3, 0) and sys.platform == 'win32': | |
575 | filename = encodeFilename(filename, True).decode(preferredencoding()) | |
8222d8de | 576 | return filename |
8222d8de | 577 | except ValueError as err: |
6febd1c1 | 578 | self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') |
8222d8de JMF |
579 | return None |
580 | ||
442c37b7 | 581 | def _match_entry(self, info_dict, incomplete): |
8222d8de JMF |
582 | """ Returns None iff the file should be downloaded """ |
583 | ||
6febd1c1 | 584 | video_title = info_dict.get('title', info_dict.get('id', 'video')) |
7012b23c PH |
585 | if 'title' in info_dict: |
586 | # This can happen when we're just evaluating the playlist | |
587 | title = info_dict['title'] | |
588 | matchtitle = self.params.get('matchtitle', False) | |
589 | if matchtitle: | |
590 | if not re.search(matchtitle, title, re.IGNORECASE): | |
6febd1c1 | 591 | return '"' + title + '" title did not match pattern "' + matchtitle + '"' |
7012b23c PH |
592 | rejecttitle = self.params.get('rejecttitle', False) |
593 | if rejecttitle: | |
594 | if re.search(rejecttitle, title, re.IGNORECASE): | |
6febd1c1 | 595 | return '"' + title + '" title matched reject pattern "' + rejecttitle + '"' |
8222d8de JMF |
596 | date = info_dict.get('upload_date', None) |
597 | if date is not None: | |
598 | dateRange = self.params.get('daterange', DateRange()) | |
599 | if date not in dateRange: | |
6febd1c1 | 600 | return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) |
5fe18bdb PH |
601 | view_count = info_dict.get('view_count', None) |
602 | if view_count is not None: | |
603 | min_views = self.params.get('min_views') | |
604 | if min_views is not None and view_count < min_views: | |
6febd1c1 | 605 | return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views) |
5fe18bdb PH |
606 | max_views = self.params.get('max_views') |
607 | if max_views is not None and view_count > max_views: | |
6febd1c1 | 608 | return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) |
05900629 | 609 | if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')): |
347de493 | 610 | return 'Skipping "%s" because it is age restricted' % video_title |
c1c9a79c | 611 | if self.in_download_archive(info_dict): |
6febd1c1 | 612 | return '%s has already been recorded in archive' % video_title |
347de493 | 613 | |
442c37b7 PH |
614 | if not incomplete: |
615 | match_filter = self.params.get('match_filter') | |
616 | if match_filter is not None: | |
617 | ret = match_filter(info_dict) | |
618 | if ret is not None: | |
619 | return ret | |
347de493 | 620 | |
8222d8de | 621 | return None |
fe7e0c98 | 622 | |
b6c45014 JMF |
623 | @staticmethod |
624 | def add_extra_info(info_dict, extra_info): | |
625 | '''Set the keys from extra_info in info dict if they are missing''' | |
626 | for key, value in extra_info.items(): | |
627 | info_dict.setdefault(key, value) | |
628 | ||
7fc3fa05 PH |
629 | def extract_info(self, url, download=True, ie_key=None, extra_info={}, |
630 | process=True): | |
8222d8de JMF |
631 | ''' |
632 | Returns a list with a dictionary for each video we find. | |
633 | If 'download', also downloads the videos. | |
634 | extra_info is a dict containing the extra values to add to each result | |
613b2d9d | 635 | ''' |
fe7e0c98 | 636 | |
8222d8de | 637 | if ie_key: |
56c73665 | 638 | ies = [self.get_info_extractor(ie_key)] |
8222d8de JMF |
639 | else: |
640 | ies = self._ies | |
641 | ||
642 | for ie in ies: | |
643 | if not ie.suitable(url): | |
644 | continue | |
645 | ||
646 | if not ie.working(): | |
6febd1c1 PH |
647 | self.report_warning('The program functionality for this site has been marked as broken, ' |
648 | 'and will probably not work.') | |
8222d8de JMF |
649 | |
650 | try: | |
651 | ie_result = ie.extract(url) | |
5f6a1245 | 652 | if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) |
8222d8de JMF |
653 | break |
654 | if isinstance(ie_result, list): | |
655 | # Backwards compatibility: old IE result format | |
8222d8de JMF |
656 | ie_result = { |
657 | '_type': 'compat_list', | |
658 | 'entries': ie_result, | |
659 | } | |
ea38e55f | 660 | self.add_default_extra_info(ie_result, ie, url) |
7fc3fa05 PH |
661 | if process: |
662 | return self.process_ie_result(ie_result, download, extra_info) | |
663 | else: | |
664 | return ie_result | |
5f6a1245 | 665 | except ExtractorError as de: # An error we somewhat expected |
8222d8de JMF |
666 | self.report_error(compat_str(de), de.format_traceback()) |
667 | break | |
d3e5bbf4 PH |
668 | except MaxDownloadsReached: |
669 | raise | |
8222d8de JMF |
670 | except Exception as e: |
671 | if self.params.get('ignoreerrors', False): | |
672 | self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) | |
673 | break | |
674 | else: | |
675 | raise | |
676 | else: | |
1a489545 | 677 | self.report_error('no suitable InfoExtractor for URL %s' % url) |
fe7e0c98 | 678 | |
ea38e55f PH |
679 | def add_default_extra_info(self, ie_result, ie, url): |
680 | self.add_extra_info(ie_result, { | |
681 | 'extractor': ie.IE_NAME, | |
682 | 'webpage_url': url, | |
683 | 'webpage_url_basename': url_basename(url), | |
684 | 'extractor_key': ie.ie_key(), | |
685 | }) | |
686 | ||
8222d8de JMF |
687 | def process_ie_result(self, ie_result, download=True, extra_info={}): |
688 | """ | |
689 | Take the result of the ie(may be modified) and resolve all unresolved | |
690 | references (URLs, playlist items). | |
691 | ||
692 | It will also download the videos if 'download'. | |
693 | Returns the resolved ie_result. | |
694 | """ | |
695 | ||
e8ee972c PH |
696 | result_type = ie_result.get('_type', 'video') |
697 | ||
057a5206 PH |
698 | if result_type in ('url', 'url_transparent'): |
699 | extract_flat = self.params.get('extract_flat', False) | |
700 | if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or | |
701 | extract_flat is True): | |
057a5206 PH |
702 | if self.params.get('forcejson', False): |
703 | self.to_stdout(json.dumps(ie_result)) | |
e8ee972c PH |
704 | return ie_result |
705 | ||
8222d8de | 706 | if result_type == 'video': |
b6c45014 | 707 | self.add_extra_info(ie_result, extra_info) |
feee2ecf | 708 | return self.process_video_result(ie_result, download=download) |
8222d8de JMF |
709 | elif result_type == 'url': |
710 | # We have to add extra_info to the results because it may be | |
711 | # contained in a playlist | |
712 | return self.extract_info(ie_result['url'], | |
713 | download, | |
714 | ie_key=ie_result.get('ie_key'), | |
715 | extra_info=extra_info) | |
7fc3fa05 PH |
716 | elif result_type == 'url_transparent': |
717 | # Use the information from the embedding page | |
718 | info = self.extract_info( | |
719 | ie_result['url'], ie_key=ie_result.get('ie_key'), | |
720 | extra_info=extra_info, download=False, process=False) | |
721 | ||
412c617d PH |
722 | force_properties = dict( |
723 | (k, v) for k, v in ie_result.items() if v is not None) | |
724 | for f in ('_type', 'url'): | |
725 | if f in force_properties: | |
726 | del force_properties[f] | |
727 | new_result = info.copy() | |
728 | new_result.update(force_properties) | |
7fc3fa05 PH |
729 | |
730 | assert new_result.get('_type') != 'url_transparent' | |
7fc3fa05 PH |
731 | |
732 | return self.process_ie_result( | |
733 | new_result, download=download, extra_info=extra_info) | |
42e12102 | 734 | elif result_type == 'playlist' or result_type == 'multi_video': |
8222d8de JMF |
735 | # We process each entry in the playlist |
736 | playlist = ie_result.get('title', None) or ie_result.get('id', None) | |
6febd1c1 | 737 | self.to_screen('[download] Downloading playlist: %s' % playlist) |
8222d8de JMF |
738 | |
739 | playlist_results = [] | |
740 | ||
8222d8de | 741 | playliststart = self.params.get('playliststart', 1) - 1 |
a19fd00c PH |
742 | playlistend = self.params.get('playlistend', None) |
743 | # For backwards compatibility, interpret -1 as whole list | |
8222d8de | 744 | if playlistend == -1: |
a19fd00c | 745 | playlistend = None |
8222d8de | 746 | |
c14e88f0 PH |
747 | playlistitems_str = self.params.get('playlist_items', None) |
748 | playlistitems = None | |
749 | if playlistitems_str is not None: | |
750 | def iter_playlistitems(format): | |
751 | for string_segment in format.split(','): | |
752 | if '-' in string_segment: | |
753 | start, end = string_segment.split('-') | |
754 | for item in range(int(start), int(end) + 1): | |
755 | yield int(item) | |
756 | else: | |
757 | yield int(string_segment) | |
758 | playlistitems = iter_playlistitems(playlistitems_str) | |
759 | ||
b82f815f PH |
760 | ie_entries = ie_result['entries'] |
761 | if isinstance(ie_entries, list): | |
762 | n_all_entries = len(ie_entries) | |
c14e88f0 PH |
763 | if playlistitems: |
764 | entries = [ie_entries[i - 1] for i in playlistitems] | |
765 | else: | |
766 | entries = ie_entries[playliststart:playlistend] | |
b7ab0590 PH |
767 | n_entries = len(entries) |
768 | self.to_screen( | |
769 | "[%s] playlist %s: Collected %d video ids (downloading %d of them)" % | |
770 | (ie_result['extractor'], playlist, n_all_entries, n_entries)) | |
b82f815f | 771 | elif isinstance(ie_entries, PagedList): |
c14e88f0 PH |
772 | if playlistitems: |
773 | entries = [] | |
774 | for item in playlistitems: | |
775 | entries.extend(ie_entries.getslice( | |
776 | item - 1, item | |
777 | )) | |
778 | else: | |
779 | entries = ie_entries.getslice( | |
780 | playliststart, playlistend) | |
b7ab0590 PH |
781 | n_entries = len(entries) |
782 | self.to_screen( | |
783 | "[%s] playlist %s: Downloading %d videos" % | |
784 | (ie_result['extractor'], playlist, n_entries)) | |
b82f815f | 785 | else: # iterable |
c14e88f0 PH |
786 | if playlistitems: |
787 | entry_list = list(ie_entries) | |
788 | entries = [entry_list[i - 1] for i in playlistitems] | |
789 | else: | |
790 | entries = list(itertools.islice( | |
791 | ie_entries, playliststart, playlistend)) | |
b82f815f PH |
792 | n_entries = len(entries) |
793 | self.to_screen( | |
794 | "[%s] playlist %s: Downloading %d videos" % | |
795 | (ie_result['extractor'], playlist, n_entries)) | |
8222d8de | 796 | |
ff815fe6 MS |
797 | if self.params.get('playlistreverse', False): |
798 | entries = entries[::-1] | |
799 | ||
fe7e0c98 | 800 | for i, entry in enumerate(entries, 1): |
734ea11e | 801 | self.to_screen('[download] Downloading video %s of %s' % (i, n_entries)) |
8222d8de | 802 | extra = { |
c6b4132a | 803 | 'n_entries': n_entries, |
fe7e0c98 | 804 | 'playlist': playlist, |
a1cf99d0 PH |
805 | 'playlist_id': ie_result.get('id'), |
806 | 'playlist_title': ie_result.get('title'), | |
fe7e0c98 | 807 | 'playlist_index': i + playliststart, |
b6c45014 | 808 | 'extractor': ie_result['extractor'], |
9103bbc5 | 809 | 'webpage_url': ie_result['webpage_url'], |
29eb5174 | 810 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 811 | 'extractor_key': ie_result['extractor_key'], |
fe7e0c98 | 812 | } |
7012b23c | 813 | |
442c37b7 | 814 | reason = self._match_entry(entry, incomplete=True) |
7012b23c | 815 | if reason is not None: |
6febd1c1 | 816 | self.to_screen('[download] ' + reason) |
7012b23c PH |
817 | continue |
818 | ||
8222d8de JMF |
819 | entry_result = self.process_ie_result(entry, |
820 | download=download, | |
821 | extra_info=extra) | |
822 | playlist_results.append(entry_result) | |
823 | ie_result['entries'] = playlist_results | |
824 | return ie_result | |
825 | elif result_type == 'compat_list': | |
c9bf4114 PH |
826 | self.report_warning( |
827 | 'Extractor %s returned a compat_list result. ' | |
828 | 'It needs to be updated.' % ie_result.get('extractor')) | |
5f6a1245 | 829 | |
8222d8de | 830 | def _fixup(r): |
9e1a5b84 JW |
831 | self.add_extra_info( |
832 | r, | |
9103bbc5 JMF |
833 | { |
834 | 'extractor': ie_result['extractor'], | |
835 | 'webpage_url': ie_result['webpage_url'], | |
29eb5174 | 836 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 837 | 'extractor_key': ie_result['extractor_key'], |
9e1a5b84 JW |
838 | } |
839 | ) | |
8222d8de JMF |
840 | return r |
841 | ie_result['entries'] = [ | |
b6c45014 | 842 | self.process_ie_result(_fixup(r), download, extra_info) |
8222d8de JMF |
843 | for r in ie_result['entries'] |
844 | ] | |
845 | return ie_result | |
846 | else: | |
847 | raise Exception('Invalid result type: %s' % result_type) | |
848 | ||
083c9df9 PH |
849 | def _apply_format_filter(self, format_spec, available_formats): |
850 | " Returns a tuple of the remaining format_spec and filtered formats " | |
851 | ||
852 | OPERATORS = { | |
853 | '<': operator.lt, | |
854 | '<=': operator.le, | |
855 | '>': operator.gt, | |
856 | '>=': operator.ge, | |
857 | '=': operator.eq, | |
858 | '!=': operator.ne, | |
859 | } | |
860 | operator_rex = re.compile(r'''(?x)\s*\[ | |
2ec19e95 | 861 | (?P<key>width|height|tbr|abr|vbr|asr|filesize|fps) |
083c9df9 PH |
862 | \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s* |
863 | (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?) | |
864 | \]$ | |
865 | ''' % '|'.join(map(re.escape, OPERATORS.keys()))) | |
866 | m = operator_rex.search(format_spec) | |
9ddb6925 S |
867 | if m: |
868 | try: | |
869 | comparison_value = int(m.group('value')) | |
870 | except ValueError: | |
871 | comparison_value = parse_filesize(m.group('value')) | |
872 | if comparison_value is None: | |
873 | comparison_value = parse_filesize(m.group('value') + 'B') | |
874 | if comparison_value is None: | |
875 | raise ValueError( | |
876 | 'Invalid value %r in format specification %r' % ( | |
877 | m.group('value'), format_spec)) | |
878 | op = OPERATORS[m.group('op')] | |
879 | ||
083c9df9 | 880 | if not m: |
9ddb6925 S |
881 | STR_OPERATORS = { |
882 | '=': operator.eq, | |
883 | '!=': operator.ne, | |
884 | } | |
885 | str_operator_rex = re.compile(r'''(?x)\s*\[ | |
886 | \s*(?P<key>ext|acodec|vcodec|container|protocol) | |
887 | \s*(?P<op>%s)(?P<none_inclusive>\s*\?)? | |
888 | \s*(?P<value>[a-zA-Z0-9_-]+) | |
889 | \s*\]$ | |
890 | ''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) | |
891 | m = str_operator_rex.search(format_spec) | |
892 | if m: | |
893 | comparison_value = m.group('value') | |
894 | op = STR_OPERATORS[m.group('op')] | |
083c9df9 | 895 | |
9ddb6925 S |
896 | if not m: |
897 | raise ValueError('Invalid format specification %r' % format_spec) | |
083c9df9 PH |
898 | |
899 | def _filter(f): | |
900 | actual_value = f.get(m.group('key')) | |
901 | if actual_value is None: | |
902 | return m.group('none_inclusive') | |
903 | return op(actual_value, comparison_value) | |
904 | new_formats = [f for f in available_formats if _filter(f)] | |
905 | ||
906 | new_format_spec = format_spec[:-len(m.group(0))] | |
907 | if not new_format_spec: | |
908 | new_format_spec = 'best' | |
909 | ||
910 | return (new_format_spec, new_formats) | |
911 | ||
a9c58ad9 | 912 | def select_format(self, format_spec, available_formats): |
083c9df9 PH |
913 | while format_spec.endswith(']'): |
914 | format_spec, available_formats = self._apply_format_filter( | |
915 | format_spec, available_formats) | |
916 | if not available_formats: | |
917 | return None | |
918 | ||
a9c58ad9 JMF |
919 | if format_spec == 'best' or format_spec is None: |
920 | return available_formats[-1] | |
921 | elif format_spec == 'worst': | |
922 | return available_formats[0] | |
ba7678f9 PH |
923 | elif format_spec == 'bestaudio': |
924 | audio_formats = [ | |
925 | f for f in available_formats | |
926 | if f.get('vcodec') == 'none'] | |
927 | if audio_formats: | |
928 | return audio_formats[-1] | |
929 | elif format_spec == 'worstaudio': | |
930 | audio_formats = [ | |
931 | f for f in available_formats | |
932 | if f.get('vcodec') == 'none'] | |
933 | if audio_formats: | |
934 | return audio_formats[0] | |
bc6d5978 JMF |
935 | elif format_spec == 'bestvideo': |
936 | video_formats = [ | |
937 | f for f in available_formats | |
938 | if f.get('acodec') == 'none'] | |
939 | if video_formats: | |
940 | return video_formats[-1] | |
941 | elif format_spec == 'worstvideo': | |
942 | video_formats = [ | |
943 | f for f in available_formats | |
944 | if f.get('acodec') == 'none'] | |
945 | if video_formats: | |
946 | return video_formats[0] | |
a9c58ad9 | 947 | else: |
0217c783 | 948 | extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav'] |
49e86983 JMF |
949 | if format_spec in extensions: |
950 | filter_f = lambda f: f['ext'] == format_spec | |
951 | else: | |
952 | filter_f = lambda f: f['format_id'] == format_spec | |
fe7e0c98 | 953 | matches = list(filter(filter_f, available_formats)) |
a9c58ad9 JMF |
954 | if matches: |
955 | return matches[-1] | |
956 | return None | |
957 | ||
e5660ee6 JMF |
958 | def _calc_headers(self, info_dict): |
959 | res = std_headers.copy() | |
960 | ||
961 | add_headers = info_dict.get('http_headers') | |
962 | if add_headers: | |
963 | res.update(add_headers) | |
964 | ||
965 | cookies = self._calc_cookies(info_dict) | |
966 | if cookies: | |
967 | res['Cookie'] = cookies | |
968 | ||
969 | return res | |
970 | ||
971 | def _calc_cookies(self, info_dict): | |
662435f7 | 972 | pr = compat_urllib_request.Request(info_dict['url']) |
e5660ee6 | 973 | self.cookiejar.add_cookie_header(pr) |
662435f7 | 974 | return pr.get_header('Cookie') |
e5660ee6 | 975 | |
dd82ffea JMF |
976 | def process_video_result(self, info_dict, download=True): |
977 | assert info_dict.get('_type', 'video') == 'video' | |
978 | ||
bec1fad2 PH |
979 | if 'id' not in info_dict: |
980 | raise ExtractorError('Missing "id" field in extractor result') | |
981 | if 'title' not in info_dict: | |
982 | raise ExtractorError('Missing "title" field in extractor result') | |
983 | ||
dd82ffea JMF |
984 | if 'playlist' not in info_dict: |
985 | # It isn't part of a playlist | |
986 | info_dict['playlist'] = None | |
987 | info_dict['playlist_index'] = None | |
988 | ||
d5519808 | 989 | thumbnails = info_dict.get('thumbnails') |
cfb56d1a PH |
990 | if thumbnails is None: |
991 | thumbnail = info_dict.get('thumbnail') | |
992 | if thumbnail: | |
a7a14d95 | 993 | info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}] |
d5519808 | 994 | if thumbnails: |
be6d7229 | 995 | thumbnails.sort(key=lambda t: ( |
cfb56d1a PH |
996 | t.get('preference'), t.get('width'), t.get('height'), |
997 | t.get('id'), t.get('url'))) | |
f6c24009 | 998 | for i, t in enumerate(thumbnails): |
d5519808 PH |
999 | if 'width' in t and 'height' in t: |
1000 | t['resolution'] = '%dx%d' % (t['width'], t['height']) | |
f6c24009 PH |
1001 | if t.get('id') is None: |
1002 | t['id'] = '%d' % i | |
d5519808 PH |
1003 | |
1004 | if thumbnails and 'thumbnail' not in info_dict: | |
1005 | info_dict['thumbnail'] = thumbnails[-1]['url'] | |
1006 | ||
c9ae7b95 | 1007 | if 'display_id' not in info_dict and 'id' in info_dict: |
0afef30b PH |
1008 | info_dict['display_id'] = info_dict['id'] |
1009 | ||
955c4514 | 1010 | if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None: |
706d7d4e S |
1011 | # Working around negative timestamps in Windows |
1012 | # (see http://bugs.python.org/issue1646728) | |
1013 | if info_dict['timestamp'] < 0 and os.name == 'nt': | |
1014 | info_dict['timestamp'] = 0 | |
9d2ecdbc | 1015 | upload_date = datetime.datetime.utcfromtimestamp( |
955c4514 | 1016 | info_dict['timestamp']) |
9d2ecdbc PH |
1017 | info_dict['upload_date'] = upload_date.strftime('%Y%m%d') |
1018 | ||
a504ced0 | 1019 | if self.params.get('listsubtitles', False): |
360e1ca5 JMF |
1020 | if 'automatic_captions' in info_dict: |
1021 | self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions') | |
1022 | self.list_subtitles(info_dict['id'], info_dict.get('subtitles'), 'subtitles') | |
a504ced0 | 1023 | return |
360e1ca5 JMF |
1024 | info_dict['requested_subtitles'] = self.process_subtitles( |
1025 | info_dict['id'], info_dict.get('subtitles'), | |
1026 | info_dict.get('automatic_captions')) | |
a504ced0 | 1027 | |
6ff000b8 | 1028 | # This extractors handle format selection themselves |
6febd1c1 | 1029 | if info_dict['extractor'] in ['Youku']: |
12893efe JMF |
1030 | if download: |
1031 | self.process_info(info_dict) | |
6ff000b8 JMF |
1032 | return info_dict |
1033 | ||
dd82ffea JMF |
1034 | # We now pick which formats have to be downloaded |
1035 | if info_dict.get('formats') is None: | |
1036 | # There's only one format available | |
1037 | formats = [info_dict] | |
1038 | else: | |
1039 | formats = info_dict['formats'] | |
1040 | ||
db95dc13 PH |
1041 | if not formats: |
1042 | raise ExtractorError('No video formats found!') | |
1043 | ||
dd82ffea | 1044 | # We check that all the formats have the format and format_id fields |
db95dc13 | 1045 | for i, format in enumerate(formats): |
bec1fad2 PH |
1046 | if 'url' not in format: |
1047 | raise ExtractorError('Missing "url" key in result (index %d)' % i) | |
1048 | ||
dd82ffea | 1049 | if format.get('format_id') is None: |
8016c922 | 1050 | format['format_id'] = compat_str(i) |
8c51aa65 | 1051 | if format.get('format') is None: |
6febd1c1 | 1052 | format['format'] = '{id} - {res}{note}'.format( |
8c51aa65 JMF |
1053 | id=format['format_id'], |
1054 | res=self.format_resolution(format), | |
6febd1c1 | 1055 | note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', |
8c51aa65 | 1056 | ) |
c1002e96 PH |
1057 | # Automatically determine file extension if missing |
1058 | if 'ext' not in format: | |
cce929ea | 1059 | format['ext'] = determine_ext(format['url']).lower() |
e5660ee6 JMF |
1060 | # Add HTTP headers, so that external programs can use them from the |
1061 | # json output | |
1062 | full_format_info = info_dict.copy() | |
1063 | full_format_info.update(format) | |
1064 | format['http_headers'] = self._calc_headers(full_format_info) | |
dd82ffea | 1065 | |
99e206d5 JMF |
1066 | format_limit = self.params.get('format_limit', None) |
1067 | if format_limit: | |
f4d96df0 PH |
1068 | formats = list(takewhile_inclusive( |
1069 | lambda f: f['format_id'] != format_limit, formats | |
1070 | )) | |
4bcc7bd1 PH |
1071 | |
1072 | # TODO Central sorting goes here | |
99e206d5 | 1073 | |
f89197d7 | 1074 | if formats[0] is not info_dict: |
b3d9ef88 JMF |
1075 | # only set the 'formats' fields if the original info_dict list them |
1076 | # otherwise we end up with a circular reference, the first (and unique) | |
f89197d7 | 1077 | # element in the 'formats' field in info_dict is info_dict itself, |
b3d9ef88 JMF |
1078 | # wich can't be exported to json |
1079 | info_dict['formats'] = formats | |
cfb56d1a | 1080 | if self.params.get('listformats'): |
bfaae0a7 | 1081 | self.list_formats(info_dict) |
1082 | return | |
cfb56d1a PH |
1083 | if self.params.get('list_thumbnails'): |
1084 | self.list_thumbnails(info_dict) | |
1085 | return | |
bfaae0a7 | 1086 | |
de3ef3ed | 1087 | req_format = self.params.get('format') |
a9c58ad9 JMF |
1088 | if req_format is None: |
1089 | req_format = 'best' | |
dd82ffea | 1090 | formats_to_download = [] |
3a77719c | 1091 | if req_format == 'all': |
dd82ffea JMF |
1092 | formats_to_download = formats |
1093 | else: | |
1de33faf PH |
1094 | for rfstr in req_format.split(','): |
1095 | # We can accept formats requested in the format: 34/5/best, we pick | |
1096 | # the first that is available, starting from left | |
1097 | req_formats = rfstr.split('/') | |
1098 | for rf in req_formats: | |
1099 | if re.match(r'.+?\+.+?', rf) is not None: | |
1100 | # Two formats have been requested like '137+139' | |
1101 | format_1, format_2 = rf.split('+') | |
1102 | formats_info = (self.select_format(format_1, formats), | |
9e1a5b84 | 1103 | self.select_format(format_2, formats)) |
1de33faf | 1104 | if all(formats_info): |
c2954908 JMF |
1105 | # The first format must contain the video and the |
1106 | # second the audio | |
1107 | if formats_info[0].get('vcodec') == 'none': | |
1108 | self.report_error('The first format must ' | |
9e1a5b84 JW |
1109 | 'contain the video, try using ' |
1110 | '"-f %s+%s"' % (format_2, format_1)) | |
c2954908 | 1111 | return |
45598f15 PH |
1112 | output_ext = ( |
1113 | formats_info[0]['ext'] | |
1114 | if self.params.get('merge_output_format') is None | |
1115 | else self.params['merge_output_format']) | |
1de33faf PH |
1116 | selected_format = { |
1117 | 'requested_formats': formats_info, | |
300753a0 S |
1118 | 'format': '%s+%s' % (formats_info[0].get('format'), |
1119 | formats_info[1].get('format')), | |
6d593c32 S |
1120 | 'format_id': '%s+%s' % (formats_info[0].get('format_id'), |
1121 | formats_info[1].get('format_id')), | |
f90ad273 PH |
1122 | 'width': formats_info[0].get('width'), |
1123 | 'height': formats_info[0].get('height'), | |
1124 | 'resolution': formats_info[0].get('resolution'), | |
1125 | 'fps': formats_info[0].get('fps'), | |
1126 | 'vcodec': formats_info[0].get('vcodec'), | |
1127 | 'vbr': formats_info[0].get('vbr'), | |
6271f1ca | 1128 | 'stretched_ratio': formats_info[0].get('stretched_ratio'), |
f90ad273 PH |
1129 | 'acodec': formats_info[1].get('acodec'), |
1130 | 'abr': formats_info[1].get('abr'), | |
45598f15 | 1131 | 'ext': output_ext, |
1de33faf PH |
1132 | } |
1133 | else: | |
1134 | selected_format = None | |
6350728b | 1135 | else: |
1de33faf PH |
1136 | selected_format = self.select_format(rf, formats) |
1137 | if selected_format is not None: | |
1138 | formats_to_download.append(selected_format) | |
1139 | break | |
dd82ffea | 1140 | if not formats_to_download: |
6febd1c1 | 1141 | raise ExtractorError('requested format not available', |
78a3a9f8 | 1142 | expected=True) |
dd82ffea JMF |
1143 | |
1144 | if download: | |
1145 | if len(formats_to_download) > 1: | |
6febd1c1 | 1146 | self.to_screen('[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) |
dd82ffea JMF |
1147 | for format in formats_to_download: |
1148 | new_info = dict(info_dict) | |
1149 | new_info.update(format) | |
1150 | self.process_info(new_info) | |
1151 | # We update the info dict with the best quality format (backwards compatibility) | |
1152 | info_dict.update(formats_to_download[-1]) | |
1153 | return info_dict | |
1154 | ||
98c70d6f | 1155 | def process_subtitles(self, video_id, normal_subtitles, automatic_captions): |
a504ced0 | 1156 | """Select the requested subtitles and their format""" |
98c70d6f JMF |
1157 | available_subs = {} |
1158 | if normal_subtitles and self.params.get('writesubtitles'): | |
1159 | available_subs.update(normal_subtitles) | |
1160 | if automatic_captions and self.params.get('writeautomaticsub'): | |
1161 | for lang, cap_info in automatic_captions.items(): | |
360e1ca5 JMF |
1162 | if lang not in available_subs: |
1163 | available_subs[lang] = cap_info | |
1164 | ||
4d171848 JMF |
1165 | if (not self.params.get('writesubtitles') and not |
1166 | self.params.get('writeautomaticsub') or not | |
1167 | available_subs): | |
1168 | return None | |
a504ced0 JMF |
1169 | |
1170 | if self.params.get('allsubtitles', False): | |
1171 | requested_langs = available_subs.keys() | |
1172 | else: | |
1173 | if self.params.get('subtitleslangs', False): | |
1174 | requested_langs = self.params.get('subtitleslangs') | |
1175 | elif 'en' in available_subs: | |
1176 | requested_langs = ['en'] | |
1177 | else: | |
1178 | requested_langs = [list(available_subs.keys())[0]] | |
1179 | ||
1180 | formats_query = self.params.get('subtitlesformat', 'best') | |
1181 | formats_preference = formats_query.split('/') if formats_query else [] | |
1182 | subs = {} | |
1183 | for lang in requested_langs: | |
1184 | formats = available_subs.get(lang) | |
1185 | if formats is None: | |
1186 | self.report_warning('%s subtitles not available for %s' % (lang, video_id)) | |
1187 | continue | |
a504ced0 JMF |
1188 | for ext in formats_preference: |
1189 | if ext == 'best': | |
1190 | f = formats[-1] | |
1191 | break | |
1192 | matches = list(filter(lambda f: f['ext'] == ext, formats)) | |
1193 | if matches: | |
1194 | f = matches[-1] | |
1195 | break | |
1196 | else: | |
1197 | f = formats[-1] | |
1198 | self.report_warning( | |
1199 | 'No subtitle format found matching "%s" for language %s, ' | |
1200 | 'using %s' % (formats_query, lang, f['ext'])) | |
1201 | subs[lang] = f | |
1202 | return subs | |
1203 | ||
8222d8de JMF |
1204 | def process_info(self, info_dict): |
1205 | """Process a single resolved IE result.""" | |
1206 | ||
1207 | assert info_dict.get('_type', 'video') == 'video' | |
fd288278 PH |
1208 | |
1209 | max_downloads = self.params.get('max_downloads') | |
1210 | if max_downloads is not None: | |
1211 | if self._num_downloads >= int(max_downloads): | |
1212 | raise MaxDownloadsReached() | |
8222d8de JMF |
1213 | |
1214 | info_dict['fulltitle'] = info_dict['title'] | |
1215 | if len(info_dict['title']) > 200: | |
6febd1c1 | 1216 | info_dict['title'] = info_dict['title'][:197] + '...' |
8222d8de | 1217 | |
11b85ce6 | 1218 | if 'format' not in info_dict: |
8222d8de JMF |
1219 | info_dict['format'] = info_dict['ext'] |
1220 | ||
442c37b7 | 1221 | reason = self._match_entry(info_dict, incomplete=False) |
8222d8de | 1222 | if reason is not None: |
6febd1c1 | 1223 | self.to_screen('[download] ' + reason) |
8222d8de JMF |
1224 | return |
1225 | ||
fd288278 | 1226 | self._num_downloads += 1 |
8222d8de | 1227 | |
e72c7e41 | 1228 | info_dict['_filename'] = filename = self.prepare_filename(info_dict) |
8222d8de JMF |
1229 | |
1230 | # Forced printings | |
1231 | if self.params.get('forcetitle', False): | |
0783b09b | 1232 | self.to_stdout(info_dict['fulltitle']) |
8222d8de | 1233 | if self.params.get('forceid', False): |
0783b09b | 1234 | self.to_stdout(info_dict['id']) |
8222d8de | 1235 | if self.params.get('forceurl', False): |
16ae61f6 | 1236 | if info_dict.get('requested_formats') is not None: |
1237 | for f in info_dict['requested_formats']: | |
1238 | self.to_stdout(f['url'] + f.get('play_path', '')) | |
1239 | else: | |
1240 | # For RTMP URLs, also include the playpath | |
1241 | self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) | |
216d71d0 | 1242 | if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: |
0783b09b | 1243 | self.to_stdout(info_dict['thumbnail']) |
216d71d0 | 1244 | if self.params.get('forcedescription', False) and info_dict.get('description') is not None: |
0783b09b | 1245 | self.to_stdout(info_dict['description']) |
8222d8de | 1246 | if self.params.get('forcefilename', False) and filename is not None: |
0783b09b | 1247 | self.to_stdout(filename) |
525ef922 PH |
1248 | if self.params.get('forceduration', False) and info_dict.get('duration') is not None: |
1249 | self.to_stdout(formatSeconds(info_dict['duration'])) | |
8222d8de | 1250 | if self.params.get('forceformat', False): |
0783b09b | 1251 | self.to_stdout(info_dict['format']) |
9d153818 | 1252 | if self.params.get('forcejson', False): |
0783b09b | 1253 | self.to_stdout(json.dumps(info_dict)) |
8222d8de JMF |
1254 | |
1255 | # Do nothing else if in simulate mode | |
1256 | if self.params.get('simulate', False): | |
1257 | return | |
1258 | ||
1259 | if filename is None: | |
1260 | return | |
1261 | ||
1262 | try: | |
e5a11a22 | 1263 | dn = os.path.dirname(sanitize_path(encodeFilename(filename))) |
d26e981d | 1264 | if dn and not os.path.exists(dn): |
8222d8de JMF |
1265 | os.makedirs(dn) |
1266 | except (OSError, IOError) as err: | |
6febd1c1 | 1267 | self.report_error('unable to create directory ' + compat_str(err)) |
8222d8de JMF |
1268 | return |
1269 | ||
1270 | if self.params.get('writedescription', False): | |
6febd1c1 | 1271 | descfn = filename + '.description' |
7b6fefc9 | 1272 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): |
6febd1c1 | 1273 | self.to_screen('[info] Video description is already present') |
f00fd51d JMF |
1274 | elif info_dict.get('description') is None: |
1275 | self.report_warning('There\'s no description to write.') | |
7b6fefc9 PH |
1276 | else: |
1277 | try: | |
6febd1c1 | 1278 | self.to_screen('[info] Writing video description to: ' + descfn) |
7b6fefc9 PH |
1279 | with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: |
1280 | descfile.write(info_dict['description']) | |
7b6fefc9 | 1281 | except (OSError, IOError): |
6febd1c1 | 1282 | self.report_error('Cannot write description file ' + descfn) |
7b6fefc9 | 1283 | return |
8222d8de | 1284 | |
1fb07d10 | 1285 | if self.params.get('writeannotations', False): |
6febd1c1 | 1286 | annofn = filename + '.annotations.xml' |
7b6fefc9 | 1287 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): |
6febd1c1 | 1288 | self.to_screen('[info] Video annotations are already present') |
7b6fefc9 PH |
1289 | else: |
1290 | try: | |
6febd1c1 | 1291 | self.to_screen('[info] Writing video annotations to: ' + annofn) |
7b6fefc9 PH |
1292 | with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: |
1293 | annofile.write(info_dict['annotations']) | |
1294 | except (KeyError, TypeError): | |
6febd1c1 | 1295 | self.report_warning('There are no annotations to write.') |
7b6fefc9 | 1296 | except (OSError, IOError): |
6febd1c1 | 1297 | self.report_error('Cannot write annotations file: ' + annofn) |
7b6fefc9 | 1298 | return |
1fb07d10 | 1299 | |
c4a91be7 | 1300 | subtitles_are_requested = any([self.params.get('writesubtitles', False), |
0b7f3118 | 1301 | self.params.get('writeautomaticsub')]) |
c4a91be7 | 1302 | |
c84dd8a9 | 1303 | if subtitles_are_requested and info_dict.get('requested_subtitles'): |
8222d8de JMF |
1304 | # subtitles download errors are already managed as troubles in relevant IE |
1305 | # that way it will silently go on when used with unsupporting IE | |
c84dd8a9 | 1306 | subtitles = info_dict['requested_subtitles'] |
0f2c0d33 | 1307 | ie = self.get_info_extractor(info_dict['extractor_key']) |
a504ced0 JMF |
1308 | for sub_lang, sub_info in subtitles.items(): |
1309 | sub_format = sub_info['ext'] | |
1310 | if sub_info.get('data') is not None: | |
1311 | sub_data = sub_info['data'] | |
1312 | else: | |
1313 | try: | |
0f2c0d33 JMF |
1314 | sub_data = ie._download_webpage( |
1315 | sub_info['url'], info_dict['id'], note=False) | |
1316 | except ExtractorError as err: | |
a504ced0 | 1317 | self.report_warning('Unable to download subtitle for "%s": %s' % |
0f2c0d33 | 1318 | (sub_lang, compat_str(err.cause))) |
a504ced0 | 1319 | continue |
8222d8de | 1320 | try: |
d4051a8e | 1321 | sub_filename = subtitles_filename(filename, sub_lang, sub_format) |
7b6fefc9 | 1322 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): |
6febd1c1 | 1323 | self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) |
7b6fefc9 | 1324 | else: |
6febd1c1 | 1325 | self.to_screen('[info] Writing video subtitles to: ' + sub_filename) |
7b6fefc9 | 1326 | with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: |
a504ced0 | 1327 | subfile.write(sub_data) |
8222d8de | 1328 | except (OSError, IOError): |
e4db1951 | 1329 | self.report_error('Cannot write subtitles file ' + sub_filename) |
8222d8de JMF |
1330 | return |
1331 | ||
8222d8de | 1332 | if self.params.get('writeinfojson', False): |
6febd1c1 | 1333 | infofn = os.path.splitext(filename)[0] + '.info.json' |
7b6fefc9 | 1334 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)): |
6febd1c1 | 1335 | self.to_screen('[info] Video description metadata is already present') |
7b6fefc9 | 1336 | else: |
6febd1c1 | 1337 | self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn) |
7b6fefc9 | 1338 | try: |
92120217 | 1339 | write_json_file(info_dict, infofn) |
7b6fefc9 | 1340 | except (OSError, IOError): |
6febd1c1 | 1341 | self.report_error('Cannot write metadata to JSON file ' + infofn) |
7b6fefc9 | 1342 | return |
8222d8de | 1343 | |
ec82d85a | 1344 | self._write_thumbnails(info_dict, filename) |
8222d8de JMF |
1345 | |
1346 | if not self.params.get('skip_download', False): | |
4340deca P |
1347 | try: |
1348 | def dl(name, info): | |
a055469f | 1349 | fd = get_suitable_downloader(info, self.params)(self, self.params) |
4340deca P |
1350 | for ph in self._progress_hooks: |
1351 | fd.add_progress_hook(ph) | |
1352 | if self.params.get('verbose'): | |
1353 | self.to_stdout('[debug] Invoking downloader on %r' % info.get('url')) | |
1354 | return fd.download(name, info) | |
ee69b99a | 1355 | |
4340deca P |
1356 | if info_dict.get('requested_formats') is not None: |
1357 | downloaded = [] | |
1358 | success = True | |
1359 | merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) | |
f740fae2 | 1360 | if not merger.available: |
4340deca P |
1361 | postprocessors = [] |
1362 | self.report_warning('You have requested multiple ' | |
1363 | 'formats but ffmpeg or avconv are not installed.' | |
1364 | ' The formats won\'t be merged') | |
6350728b | 1365 | else: |
4340deca P |
1366 | postprocessors = [merger] |
1367 | for f in info_dict['requested_formats']: | |
1368 | new_info = dict(info_dict) | |
1369 | new_info.update(f) | |
1370 | fname = self.prepare_filename(new_info) | |
1371 | fname = prepend_extension(fname, 'f%s' % f['format_id']) | |
1372 | downloaded.append(fname) | |
1373 | partial_success = dl(fname, new_info) | |
1374 | success = success and partial_success | |
1375 | info_dict['__postprocessors'] = postprocessors | |
1376 | info_dict['__files_to_merge'] = downloaded | |
1377 | else: | |
1378 | # Just a single file | |
1379 | success = dl(filename, info_dict) | |
1380 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1381 | self.report_error('unable to download video data: %s' % str(err)) | |
1382 | return | |
1383 | except (OSError, IOError) as err: | |
1384 | raise UnavailableVideoError(err) | |
1385 | except (ContentTooShortError, ) as err: | |
1386 | self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) | |
1387 | return | |
8222d8de JMF |
1388 | |
1389 | if success: | |
6271f1ca | 1390 | # Fixup content |
62cd676c PH |
1391 | fixup_policy = self.params.get('fixup') |
1392 | if fixup_policy is None: | |
1393 | fixup_policy = 'detect_or_warn' | |
1394 | ||
6271f1ca PH |
1395 | stretched_ratio = info_dict.get('stretched_ratio') |
1396 | if stretched_ratio is not None and stretched_ratio != 1: | |
6271f1ca PH |
1397 | if fixup_policy == 'warn': |
1398 | self.report_warning('%s: Non-uniform pixel ratio (%s)' % ( | |
1399 | info_dict['id'], stretched_ratio)) | |
1400 | elif fixup_policy == 'detect_or_warn': | |
1401 | stretched_pp = FFmpegFixupStretchedPP(self) | |
1402 | if stretched_pp.available: | |
1403 | info_dict.setdefault('__postprocessors', []) | |
1404 | info_dict['__postprocessors'].append(stretched_pp) | |
1405 | else: | |
1406 | self.report_warning( | |
1407 | '%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % ( | |
1408 | info_dict['id'], stretched_ratio)) | |
1409 | else: | |
62cd676c PH |
1410 | assert fixup_policy in ('ignore', 'never') |
1411 | ||
1412 | if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash': | |
1413 | if fixup_policy == 'warn': | |
1414 | self.report_warning('%s: writing DASH m4a. Only some players support this container.' % ( | |
1415 | info_dict['id'])) | |
1416 | elif fixup_policy == 'detect_or_warn': | |
1417 | fixup_pp = FFmpegFixupM4aPP(self) | |
1418 | if fixup_pp.available: | |
1419 | info_dict.setdefault('__postprocessors', []) | |
1420 | info_dict['__postprocessors'].append(fixup_pp) | |
1421 | else: | |
1422 | self.report_warning( | |
1423 | '%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % ( | |
1424 | info_dict['id'])) | |
1425 | else: | |
1426 | assert fixup_policy in ('ignore', 'never') | |
6271f1ca | 1427 | |
8222d8de JMF |
1428 | try: |
1429 | self.post_process(filename, info_dict) | |
1430 | except (PostProcessingError) as err: | |
6febd1c1 | 1431 | self.report_error('postprocessing: %s' % str(err)) |
8222d8de | 1432 | return |
cd58dc3e | 1433 | self.record_download_archive(info_dict) |
8222d8de JMF |
1434 | |
1435 | def download(self, url_list): | |
1436 | """Download a given list of URLs.""" | |
acd69589 | 1437 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
0c75c3fa | 1438 | if (len(url_list) > 1 and |
8fb3ac36 PH |
1439 | '%' not in outtmpl and |
1440 | self.params.get('max_downloads') != 1): | |
acd69589 | 1441 | raise SameFileError(outtmpl) |
8222d8de JMF |
1442 | |
1443 | for url in url_list: | |
1444 | try: | |
5f6a1245 | 1445 | # It also downloads the videos |
63e0be34 | 1446 | res = self.extract_info(url) |
8222d8de | 1447 | except UnavailableVideoError: |
6febd1c1 | 1448 | self.report_error('unable to download video') |
8222d8de | 1449 | except MaxDownloadsReached: |
6febd1c1 | 1450 | self.to_screen('[info] Maximum number of downloaded files reached.') |
8222d8de | 1451 | raise |
63e0be34 PH |
1452 | else: |
1453 | if self.params.get('dump_single_json', False): | |
1454 | self.to_stdout(json.dumps(res)) | |
8222d8de JMF |
1455 | |
1456 | return self._download_retcode | |
1457 | ||
1dcc4c0c | 1458 | def download_with_info_file(self, info_filename): |
31bd3925 JMF |
1459 | with contextlib.closing(fileinput.FileInput( |
1460 | [info_filename], mode='r', | |
1461 | openhook=fileinput.hook_encoded('utf-8'))) as f: | |
1462 | # FileInput doesn't have a read method, we can't call json.load | |
1463 | info = json.loads('\n'.join(f)) | |
d4943898 JMF |
1464 | try: |
1465 | self.process_ie_result(info, download=True) | |
1466 | except DownloadError: | |
1467 | webpage_url = info.get('webpage_url') | |
1468 | if webpage_url is not None: | |
6febd1c1 | 1469 | self.report_warning('The info failed to download, trying with "%s"' % webpage_url) |
d4943898 JMF |
1470 | return self.download([webpage_url]) |
1471 | else: | |
1472 | raise | |
1473 | return self._download_retcode | |
1dcc4c0c | 1474 | |
8222d8de JMF |
1475 | def post_process(self, filename, ie_info): |
1476 | """Run all the postprocessors on the given file.""" | |
1477 | info = dict(ie_info) | |
1478 | info['filepath'] = filename | |
6350728b JMF |
1479 | pps_chain = [] |
1480 | if ie_info.get('__postprocessors') is not None: | |
1481 | pps_chain.extend(ie_info['__postprocessors']) | |
1482 | pps_chain.extend(self._pps) | |
1483 | for pp in pps_chain: | |
f3ff1a36 JMF |
1484 | keep_video = None |
1485 | old_filename = info['filepath'] | |
8222d8de | 1486 | try: |
f3ff1a36 | 1487 | keep_video_wish, info = pp.run(info) |
8222d8de JMF |
1488 | if keep_video_wish is not None: |
1489 | if keep_video_wish: | |
1490 | keep_video = keep_video_wish | |
1491 | elif keep_video is None: | |
1492 | # No clear decision yet, let IE decide | |
1493 | keep_video = keep_video_wish | |
1494 | except PostProcessingError as e: | |
bbcbf4d4 | 1495 | self.report_error(e.msg) |
f3ff1a36 JMF |
1496 | if keep_video is False and not self.params.get('keepvideo', False): |
1497 | try: | |
1498 | self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename) | |
1499 | os.remove(encodeFilename(old_filename)) | |
1500 | except (IOError, OSError): | |
1501 | self.report_warning('Unable to remove downloaded video file') | |
c1c9a79c | 1502 | |
5db07df6 PH |
1503 | def _make_archive_id(self, info_dict): |
1504 | # Future-proof against any change in case | |
1505 | # and backwards compatibility with prior versions | |
d31209a1 | 1506 | extractor = info_dict.get('extractor_key') |
7012b23c PH |
1507 | if extractor is None: |
1508 | if 'id' in info_dict: | |
1509 | extractor = info_dict.get('ie_key') # key in a playlist | |
1510 | if extractor is None: | |
5db07df6 | 1511 | return None # Incomplete video information |
6febd1c1 | 1512 | return extractor.lower() + ' ' + info_dict['id'] |
5db07df6 PH |
1513 | |
1514 | def in_download_archive(self, info_dict): | |
1515 | fn = self.params.get('download_archive') | |
1516 | if fn is None: | |
1517 | return False | |
1518 | ||
1519 | vid_id = self._make_archive_id(info_dict) | |
1520 | if vid_id is None: | |
7012b23c | 1521 | return False # Incomplete video information |
5db07df6 | 1522 | |
c1c9a79c PH |
1523 | try: |
1524 | with locked_file(fn, 'r', encoding='utf-8') as archive_file: | |
1525 | for line in archive_file: | |
1526 | if line.strip() == vid_id: | |
1527 | return True | |
1528 | except IOError as ioe: | |
1529 | if ioe.errno != errno.ENOENT: | |
1530 | raise | |
1531 | return False | |
1532 | ||
1533 | def record_download_archive(self, info_dict): | |
1534 | fn = self.params.get('download_archive') | |
1535 | if fn is None: | |
1536 | return | |
5db07df6 PH |
1537 | vid_id = self._make_archive_id(info_dict) |
1538 | assert vid_id | |
c1c9a79c | 1539 | with locked_file(fn, 'a', encoding='utf-8') as archive_file: |
6febd1c1 | 1540 | archive_file.write(vid_id + '\n') |
dd82ffea | 1541 | |
8c51aa65 | 1542 | @staticmethod |
8abeeb94 | 1543 | def format_resolution(format, default='unknown'): |
fb04e403 PH |
1544 | if format.get('vcodec') == 'none': |
1545 | return 'audio only' | |
f49d89ee PH |
1546 | if format.get('resolution') is not None: |
1547 | return format['resolution'] | |
8c51aa65 JMF |
1548 | if format.get('height') is not None: |
1549 | if format.get('width') is not None: | |
6febd1c1 | 1550 | res = '%sx%s' % (format['width'], format['height']) |
8c51aa65 | 1551 | else: |
6febd1c1 | 1552 | res = '%sp' % format['height'] |
f49d89ee | 1553 | elif format.get('width') is not None: |
6febd1c1 | 1554 | res = '?x%d' % format['width'] |
8c51aa65 | 1555 | else: |
8abeeb94 | 1556 | res = default |
8c51aa65 JMF |
1557 | return res |
1558 | ||
c57f7757 PH |
1559 | def _format_note(self, fdict): |
1560 | res = '' | |
1561 | if fdict.get('ext') in ['f4f', 'f4m']: | |
1562 | res += '(unsupported) ' | |
1563 | if fdict.get('format_note') is not None: | |
1564 | res += fdict['format_note'] + ' ' | |
1565 | if fdict.get('tbr') is not None: | |
1566 | res += '%4dk ' % fdict['tbr'] | |
1567 | if fdict.get('container') is not None: | |
1568 | if res: | |
1569 | res += ', ' | |
1570 | res += '%s container' % fdict['container'] | |
1571 | if (fdict.get('vcodec') is not None and | |
1572 | fdict.get('vcodec') != 'none'): | |
1573 | if res: | |
1574 | res += ', ' | |
1575 | res += fdict['vcodec'] | |
91c7271a | 1576 | if fdict.get('vbr') is not None: |
c57f7757 PH |
1577 | res += '@' |
1578 | elif fdict.get('vbr') is not None and fdict.get('abr') is not None: | |
1579 | res += 'video@' | |
1580 | if fdict.get('vbr') is not None: | |
1581 | res += '%4dk' % fdict['vbr'] | |
fbb21cf5 PH |
1582 | if fdict.get('fps') is not None: |
1583 | res += ', %sfps' % fdict['fps'] | |
c57f7757 PH |
1584 | if fdict.get('acodec') is not None: |
1585 | if res: | |
1586 | res += ', ' | |
1587 | if fdict['acodec'] == 'none': | |
1588 | res += 'video only' | |
1589 | else: | |
1590 | res += '%-5s' % fdict['acodec'] | |
1591 | elif fdict.get('abr') is not None: | |
1592 | if res: | |
1593 | res += ', ' | |
1594 | res += 'audio' | |
1595 | if fdict.get('abr') is not None: | |
1596 | res += '@%3dk' % fdict['abr'] | |
1597 | if fdict.get('asr') is not None: | |
1598 | res += ' (%5dHz)' % fdict['asr'] | |
1599 | if fdict.get('filesize') is not None: | |
1600 | if res: | |
1601 | res += ', ' | |
1602 | res += format_bytes(fdict['filesize']) | |
9732d77e PH |
1603 | elif fdict.get('filesize_approx') is not None: |
1604 | if res: | |
1605 | res += ', ' | |
1606 | res += '~' + format_bytes(fdict['filesize_approx']) | |
c57f7757 | 1607 | return res |
91c7271a | 1608 | |
c57f7757 | 1609 | def list_formats(self, info_dict): |
94badb25 | 1610 | formats = info_dict.get('formats', [info_dict]) |
b81a359e PH |
1611 | table = [ |
1612 | [f['format_id'], f['ext'], self.format_resolution(f), self._format_note(f)] | |
1613 | for f in formats | |
e65566a9 | 1614 | if f.get('preference') is None or f['preference'] >= -1000] |
94badb25 | 1615 | if len(formats) > 1: |
b81a359e | 1616 | table[-1][-1] += (' ' if table[-1][-1] else '') + '(best)' |
57dd9a8f | 1617 | |
b81a359e | 1618 | header_line = ['format code', 'extension', 'resolution', 'note'] |
cfb56d1a | 1619 | self.to_screen( |
b81a359e PH |
1620 | '[info] Available formats for %s:\n%s' % |
1621 | (info_dict['id'], render_table(header_line, table))) | |
cfb56d1a PH |
1622 | |
1623 | def list_thumbnails(self, info_dict): | |
1624 | thumbnails = info_dict.get('thumbnails') | |
1625 | if not thumbnails: | |
1626 | tn_url = info_dict.get('thumbnail') | |
1627 | if tn_url: | |
1628 | thumbnails = [{'id': '0', 'url': tn_url}] | |
1629 | else: | |
1630 | self.to_screen( | |
1631 | '[info] No thumbnails present for %s' % info_dict['id']) | |
1632 | return | |
1633 | ||
1634 | self.to_screen( | |
1635 | '[info] Thumbnails for %s:' % info_dict['id']) | |
1636 | self.to_screen(render_table( | |
1637 | ['ID', 'width', 'height', 'URL'], | |
1638 | [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails])) | |
dca08720 | 1639 | |
360e1ca5 | 1640 | def list_subtitles(self, video_id, subtitles, name='subtitles'): |
a504ced0 | 1641 | if not subtitles: |
360e1ca5 | 1642 | self.to_screen('%s has no %s' % (video_id, name)) |
a504ced0 | 1643 | return |
a504ced0 | 1644 | self.to_screen( |
edab9dbf JMF |
1645 | 'Available %s for %s:' % (name, video_id)) |
1646 | self.to_screen(render_table( | |
1647 | ['Language', 'formats'], | |
1648 | [[lang, ', '.join(f['ext'] for f in reversed(formats))] | |
1649 | for lang, formats in subtitles.items()])) | |
a504ced0 | 1650 | |
dca08720 PH |
1651 | def urlopen(self, req): |
1652 | """ Start an HTTP download """ | |
37419b4f | 1653 | |
d05cfe06 S |
1654 | # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not |
1655 | # always respected by websites, some tend to give out URLs with non percent-encoded | |
1656 | # non-ASCII characters (see telemb.py, ard.py [#3412]) | |
37419b4f | 1657 | # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991) |
d05cfe06 S |
1658 | # To work around aforementioned issue we will replace request's original URL with |
1659 | # percent-encoded one | |
8f9312c3 | 1660 | req_is_string = isinstance(req, compat_basestring) |
68b09730 | 1661 | url = req if req_is_string else req.get_full_url() |
d05cfe06 | 1662 | url_escaped = escape_url(url) |
37419b4f S |
1663 | |
1664 | # Substitute URL if any change after escaping | |
1665 | if url != url_escaped: | |
68b09730 | 1666 | if req_is_string: |
37419b4f S |
1667 | req = url_escaped |
1668 | else: | |
1669 | req = compat_urllib_request.Request( | |
1670 | url_escaped, data=req.data, headers=req.headers, | |
1671 | origin_req_host=req.origin_req_host, unverifiable=req.unverifiable) | |
1672 | ||
19a41fc6 | 1673 | return self._opener.open(req, timeout=self._socket_timeout) |
dca08720 PH |
1674 | |
1675 | def print_debug_header(self): | |
1676 | if not self.params.get('verbose'): | |
1677 | return | |
62fec3b2 | 1678 | |
4192b51c PH |
1679 | if type('') is not compat_str: |
1680 | # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326) | |
1681 | self.report_warning( | |
1682 | 'Your Python is broken! Update to a newer and supported version') | |
1683 | ||
c6afed48 PH |
1684 | stdout_encoding = getattr( |
1685 | sys.stdout, 'encoding', 'missing (%s)' % type(sys.stdout).__name__) | |
b0472057 | 1686 | encoding_str = ( |
734f90bb PH |
1687 | '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( |
1688 | locale.getpreferredencoding(), | |
1689 | sys.getfilesystemencoding(), | |
c6afed48 | 1690 | stdout_encoding, |
b0472057 | 1691 | self.get_encoding())) |
4192b51c | 1692 | write_string(encoding_str, encoding=None) |
734f90bb PH |
1693 | |
1694 | self._write_string('[debug] youtube-dl version ' + __version__ + '\n') | |
dca08720 PH |
1695 | try: |
1696 | sp = subprocess.Popen( | |
1697 | ['git', 'rev-parse', '--short', 'HEAD'], | |
1698 | stdout=subprocess.PIPE, stderr=subprocess.PIPE, | |
1699 | cwd=os.path.dirname(os.path.abspath(__file__))) | |
1700 | out, err = sp.communicate() | |
1701 | out = out.decode().strip() | |
1702 | if re.match('[0-9a-f]+', out): | |
734f90bb | 1703 | self._write_string('[debug] Git HEAD: ' + out + '\n') |
dca08720 PH |
1704 | except: |
1705 | try: | |
1706 | sys.exc_clear() | |
1707 | except: | |
1708 | pass | |
d28b5171 PH |
1709 | self._write_string('[debug] Python version %s - %s\n' % ( |
1710 | platform.python_version(), platform_name())) | |
1711 | ||
73fac4e9 | 1712 | exe_versions = FFmpegPostProcessor.get_versions(self) |
4c83c967 | 1713 | exe_versions['rtmpdump'] = rtmpdump_version() |
d28b5171 PH |
1714 | exe_str = ', '.join( |
1715 | '%s %s' % (exe, v) | |
1716 | for exe, v in sorted(exe_versions.items()) | |
1717 | if v | |
1718 | ) | |
1719 | if not exe_str: | |
1720 | exe_str = 'none' | |
1721 | self._write_string('[debug] exe versions: %s\n' % exe_str) | |
dca08720 PH |
1722 | |
1723 | proxy_map = {} | |
1724 | for handler in self._opener.handlers: | |
1725 | if hasattr(handler, 'proxies'): | |
1726 | proxy_map.update(handler.proxies) | |
734f90bb | 1727 | self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') |
dca08720 | 1728 | |
58b1f00d PH |
1729 | if self.params.get('call_home', False): |
1730 | ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8') | |
1731 | self._write_string('[debug] Public IP address: %s\n' % ipaddr) | |
1732 | latest_version = self.urlopen( | |
1733 | 'https://yt-dl.org/latest/version').read().decode('utf-8') | |
1734 | if version_tuple(latest_version) > version_tuple(__version__): | |
1735 | self.report_warning( | |
1736 | 'You are using an outdated version (newest version: %s)! ' | |
1737 | 'See https://yt-dl.org/update if you need help updating.' % | |
1738 | latest_version) | |
1739 | ||
e344693b | 1740 | def _setup_opener(self): |
6ad14cab | 1741 | timeout_val = self.params.get('socket_timeout') |
19a41fc6 | 1742 | self._socket_timeout = 600 if timeout_val is None else float(timeout_val) |
6ad14cab | 1743 | |
dca08720 PH |
1744 | opts_cookiefile = self.params.get('cookiefile') |
1745 | opts_proxy = self.params.get('proxy') | |
1746 | ||
1747 | if opts_cookiefile is None: | |
1748 | self.cookiejar = compat_cookiejar.CookieJar() | |
1749 | else: | |
1750 | self.cookiejar = compat_cookiejar.MozillaCookieJar( | |
1751 | opts_cookiefile) | |
1752 | if os.access(opts_cookiefile, os.R_OK): | |
1753 | self.cookiejar.load() | |
1754 | ||
1755 | cookie_processor = compat_urllib_request.HTTPCookieProcessor( | |
1756 | self.cookiejar) | |
1757 | if opts_proxy is not None: | |
1758 | if opts_proxy == '': | |
1759 | proxies = {} | |
1760 | else: | |
1761 | proxies = {'http': opts_proxy, 'https': opts_proxy} | |
1762 | else: | |
1763 | proxies = compat_urllib_request.getproxies() | |
1764 | # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) | |
1765 | if 'http' in proxies and 'https' not in proxies: | |
1766 | proxies['https'] = proxies['http'] | |
91410c9b | 1767 | proxy_handler = PerRequestProxyHandler(proxies) |
a0ddb8a2 PH |
1768 | |
1769 | debuglevel = 1 if self.params.get('debug_printtraffic') else 0 | |
be4a824d PH |
1770 | https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) |
1771 | ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) | |
dca08720 | 1772 | opener = compat_urllib_request.build_opener( |
2461f79d PH |
1773 | proxy_handler, https_handler, cookie_processor, ydlh) |
1774 | ||
dca08720 PH |
1775 | # Delete the default user-agent header, which would otherwise apply in |
1776 | # cases where our custom HTTP handler doesn't come into play | |
1777 | # (See https://github.com/rg3/youtube-dl/issues/1309 for details) | |
1778 | opener.addheaders = [] | |
1779 | self._opener = opener | |
62fec3b2 PH |
1780 | |
1781 | def encode(self, s): | |
1782 | if isinstance(s, bytes): | |
1783 | return s # Already encoded | |
1784 | ||
1785 | try: | |
1786 | return s.encode(self.get_encoding()) | |
1787 | except UnicodeEncodeError as err: | |
1788 | err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.' | |
1789 | raise | |
1790 | ||
1791 | def get_encoding(self): | |
1792 | encoding = self.params.get('encoding') | |
1793 | if encoding is None: | |
1794 | encoding = preferredencoding() | |
1795 | return encoding | |
ec82d85a PH |
1796 | |
1797 | def _write_thumbnails(self, info_dict, filename): | |
1798 | if self.params.get('writethumbnail', False): | |
1799 | thumbnails = info_dict.get('thumbnails') | |
1800 | if thumbnails: | |
1801 | thumbnails = [thumbnails[-1]] | |
1802 | elif self.params.get('write_all_thumbnails', False): | |
1803 | thumbnails = info_dict.get('thumbnails') | |
1804 | else: | |
1805 | return | |
1806 | ||
1807 | if not thumbnails: | |
1808 | # No thumbnails present, so return immediately | |
1809 | return | |
1810 | ||
1811 | for t in thumbnails: | |
1812 | thumb_ext = determine_ext(t['url'], 'jpg') | |
1813 | suffix = '_%s' % t['id'] if len(thumbnails) > 1 else '' | |
1814 | thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else '' | |
1815 | thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext | |
1816 | ||
1817 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)): | |
1818 | self.to_screen('[%s] %s: Thumbnail %sis already present' % | |
1819 | (info_dict['extractor'], info_dict['id'], thumb_display_id)) | |
1820 | else: | |
1821 | self.to_screen('[%s] %s: Downloading thumbnail %s...' % | |
1822 | (info_dict['extractor'], info_dict['id'], thumb_display_id)) | |
1823 | try: | |
1824 | uf = self.urlopen(t['url']) | |
1825 | with open(thumb_filename, 'wb') as thumbf: | |
1826 | shutil.copyfileobj(uf, thumbf) | |
1827 | self.to_screen('[%s] %s: Writing thumbnail %sto: %s' % | |
1828 | (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename)) | |
1829 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
1830 | self.report_warning('Unable to download thumbnail "%s": %s' % | |
1831 | (t['url'], compat_str(err))) |