]>
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 |
b82f815f | 10 | import itertools |
8694c600 | 11 | import json |
62fec3b2 | 12 | import locale |
8222d8de | 13 | import os |
dca08720 | 14 | import platform |
8222d8de JMF |
15 | import re |
16 | import shutil | |
dca08720 | 17 | import subprocess |
8222d8de JMF |
18 | import socket |
19 | import sys | |
20 | import time | |
21 | import traceback | |
22 | ||
1e5b9a95 PH |
23 | if os.name == 'nt': |
24 | import ctypes | |
25 | ||
8c25f81b | 26 | from .compat import ( |
dca08720 | 27 | compat_cookiejar, |
4644ac55 | 28 | compat_expanduser, |
ce02ed60 | 29 | compat_http_client, |
4f026faf | 30 | compat_kwargs, |
ce02ed60 PH |
31 | compat_str, |
32 | compat_urllib_error, | |
33 | compat_urllib_request, | |
8c25f81b PH |
34 | ) |
35 | from .utils import ( | |
d05cfe06 | 36 | escape_url, |
ce02ed60 PH |
37 | ContentTooShortError, |
38 | date_from_str, | |
39 | DateRange, | |
acd69589 | 40 | DEFAULT_OUTTMPL, |
ce02ed60 PH |
41 | determine_ext, |
42 | DownloadError, | |
43 | encodeFilename, | |
44 | ExtractorError, | |
02dbf93f | 45 | format_bytes, |
525ef922 | 46 | formatSeconds, |
1c088fa8 | 47 | get_term_width, |
ce02ed60 | 48 | locked_file, |
dca08720 | 49 | make_HTTPS_handler, |
ce02ed60 | 50 | MaxDownloadsReached, |
b7ab0590 | 51 | PagedList, |
ce02ed60 | 52 | PostProcessingError, |
dca08720 | 53 | platform_name, |
ce02ed60 PH |
54 | preferredencoding, |
55 | SameFileError, | |
56 | sanitize_filename, | |
57 | subtitles_filename, | |
58 | takewhile_inclusive, | |
59 | UnavailableVideoError, | |
29eb5174 | 60 | url_basename, |
ce02ed60 PH |
61 | write_json_file, |
62 | write_string, | |
dca08720 | 63 | YoutubeDLHandler, |
6350728b | 64 | prepend_extension, |
7d4111ed | 65 | args_to_str, |
ce02ed60 | 66 | ) |
a0e07d31 | 67 | from .cache import Cache |
023fa8c4 | 68 | from .extractor import get_info_extractor, gen_extractors |
3bc2ddcc | 69 | from .downloader import get_suitable_downloader |
4c83c967 | 70 | from .downloader.rtmp import rtmpdump_version |
4f026faf PH |
71 | from .postprocessor import ( |
72 | FFmpegMergerPP, | |
73 | FFmpegPostProcessor, | |
74 | get_postprocessor, | |
75 | ) | |
dca08720 | 76 | from .version import __version__ |
8222d8de JMF |
77 | |
78 | ||
79 | class YoutubeDL(object): | |
80 | """YoutubeDL class. | |
81 | ||
82 | YoutubeDL objects are the ones responsible of downloading the | |
83 | actual video file and writing it to disk if the user has requested | |
84 | it, among some other tasks. In most cases there should be one per | |
85 | program. As, given a video URL, the downloader doesn't know how to | |
86 | extract all the needed information, task that InfoExtractors do, it | |
87 | has to pass the URL to one of them. | |
88 | ||
89 | For this, YoutubeDL objects have a method that allows | |
90 | InfoExtractors to be registered in a given order. When it is passed | |
91 | a URL, the YoutubeDL object handles it to the first InfoExtractor it | |
92 | finds that reports being able to handle it. The InfoExtractor extracts | |
93 | all the information about the video or videos the URL refers to, and | |
94 | YoutubeDL process the extracted information, possibly using a File | |
95 | Downloader to download the video. | |
96 | ||
97 | YoutubeDL objects accept a lot of parameters. In order not to saturate | |
98 | the object constructor with arguments, it receives a dictionary of | |
99 | options instead. These options are available through the params | |
100 | attribute for the InfoExtractors to use. The YoutubeDL also | |
101 | registers itself as the downloader in charge for the InfoExtractors | |
102 | that are added to it, so this is a "mutual registration". | |
103 | ||
104 | Available options: | |
105 | ||
106 | username: Username for authentication purposes. | |
107 | password: Password for authentication purposes. | |
c6c19746 | 108 | videopassword: Password for acces a video. |
8222d8de JMF |
109 | usenetrc: Use netrc for authentication instead. |
110 | verbose: Print additional info to stdout. | |
111 | quiet: Do not print messages to stdout. | |
ad8915b7 | 112 | no_warnings: Do not print out anything for warnings. |
8222d8de JMF |
113 | forceurl: Force printing final URL. |
114 | forcetitle: Force printing title. | |
115 | forceid: Force printing ID. | |
116 | forcethumbnail: Force printing thumbnail URL. | |
117 | forcedescription: Force printing description. | |
118 | forcefilename: Force printing final filename. | |
525ef922 | 119 | forceduration: Force printing duration. |
8694c600 | 120 | forcejson: Force printing info_dict as JSON. |
63e0be34 PH |
121 | dump_single_json: Force printing the info_dict of the whole playlist |
122 | (or video) as a single JSON line. | |
8222d8de | 123 | simulate: Do not download the video files. |
d8600787 | 124 | format: Video format code. See options.py for more information. |
8222d8de JMF |
125 | format_limit: Highest quality format to try. |
126 | outtmpl: Template for output names. | |
127 | restrictfilenames: Do not allow "&" and spaces in file names | |
128 | ignoreerrors: Do not stop on download errors. | |
129 | nooverwrites: Prevent overwriting files. | |
130 | playliststart: Playlist item to start at. | |
131 | playlistend: Playlist item to end at. | |
ff815fe6 | 132 | playlistreverse: Download playlist items in reverse order. |
8222d8de JMF |
133 | matchtitle: Download only matching titles. |
134 | rejecttitle: Reject downloads for matching titles. | |
8bf9319e | 135 | logger: Log messages to a logging.Logger instance. |
8222d8de JMF |
136 | logtostderr: Log messages to stderr instead of stdout. |
137 | writedescription: Write the video description to a .description file | |
138 | writeinfojson: Write the video description to a .info.json file | |
1fb07d10 | 139 | writeannotations: Write the video annotations to a .annotations.xml file |
8222d8de JMF |
140 | writethumbnail: Write the thumbnail image to a file |
141 | writesubtitles: Write the video subtitles to a file | |
b004821f | 142 | writeautomaticsub: Write the automatic subtitles to a file |
8222d8de | 143 | allsubtitles: Downloads all the subtitles of the video |
0b7f3118 | 144 | (requires writesubtitles or writeautomaticsub) |
8222d8de | 145 | listsubtitles: Lists all available subtitles for the video |
b98a6b2f | 146 | subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt) |
aa6a10c4 | 147 | subtitleslangs: List of languages of the subtitles to download |
8222d8de JMF |
148 | keepvideo: Keep the video file after post-processing |
149 | daterange: A DateRange object, download only if the upload_date is in the range. | |
150 | skip_download: Skip the actual download of the video file | |
c35f9e72 | 151 | cachedir: Location of the cache files in the filesystem. |
a0e07d31 | 152 | False to disable filesystem cache. |
47192f92 | 153 | noplaylist: Download single video instead of a playlist if in doubt. |
8dbe9899 PH |
154 | age_limit: An integer representing the user's age in years. |
155 | Unsuitable videos for the given age are skipped. | |
5fe18bdb PH |
156 | min_views: An integer representing the minimum view count the video |
157 | must have in order to not be skipped. | |
158 | Videos without view count information are always | |
159 | downloaded. None for no limit. | |
160 | max_views: An integer representing the maximum view count. | |
161 | Videos that are more popular than that are not | |
162 | downloaded. | |
163 | Videos without view count information are always | |
164 | downloaded. None for no limit. | |
165 | download_archive: File name of a file where all downloads are recorded. | |
c1c9a79c PH |
166 | Videos already present in the file are not downloaded |
167 | again. | |
dca08720 | 168 | cookiefile: File name where cookies should be read from and dumped to. |
a1ee09e8 | 169 | nocheckcertificate:Do not verify SSL certificates |
7e8c0af0 PH |
170 | prefer_insecure: Use HTTP instead of HTTPS to retrieve information. |
171 | At the moment, this is only supported by YouTube. | |
a1ee09e8 | 172 | proxy: URL of the proxy server to use |
e344693b | 173 | socket_timeout: Time to wait for unresponsive hosts, in seconds |
0783b09b PH |
174 | bidi_workaround: Work around buggy terminals without bidirectional text |
175 | support, using fridibi | |
a0ddb8a2 | 176 | debug_printtraffic:Print out sent and received HTTP traffic |
7b0817e8 | 177 | include_ads: Download ads as well |
04b4d394 PH |
178 | default_search: Prepend this string if an input url is not valid. |
179 | 'auto' for elaborate guessing | |
62fec3b2 | 180 | encoding: Use this encoding instead of the system-specified. |
e8ee972c | 181 | extract_flat: Do not resolve URLs, return the immediate result. |
057a5206 PH |
182 | Pass in 'in_playlist' to only show this behavior for |
183 | playlist items. | |
4f026faf | 184 | postprocessors: A list of dictionaries, each with an entry |
71b640cc PH |
185 | * key: The name of the postprocessor. See |
186 | youtube_dl/postprocessor/__init__.py for a list. | |
4f026faf PH |
187 | as well as any further keyword arguments for the |
188 | postprocessor. | |
71b640cc PH |
189 | progress_hooks: A list of functions that get called on download |
190 | progress, with a dictionary with the entries | |
191 | * filename: The final filename | |
192 | * status: One of "downloading" and "finished" | |
193 | ||
194 | The dict may also have some of the following entries: | |
195 | ||
196 | * downloaded_bytes: Bytes on disk | |
197 | * total_bytes: Size of the whole file, None if unknown | |
198 | * tmpfilename: The filename we're currently writing to | |
199 | * eta: The estimated time in seconds, None if unknown | |
200 | * speed: The download speed in bytes/second, None if | |
201 | unknown | |
202 | ||
203 | Progress hooks are guaranteed to be called at least once | |
204 | (with status "finished") if the download is successful. | |
205 | ||
fe7e0c98 | 206 | |
8222d8de JMF |
207 | The following parameters are not used by YoutubeDL itself, they are used by |
208 | the FileDownloader: | |
209 | nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, | |
210 | noresizebuffer, retries, continuedl, noprogress, consoletitle | |
76b1bd67 JMF |
211 | |
212 | The following options are used by the post processors: | |
213 | prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, | |
214 | otherwise prefer avconv. | |
8d31fa3c | 215 | exec_cmd: Arbitrary command to run after downloading |
8222d8de JMF |
216 | """ |
217 | ||
218 | params = None | |
219 | _ies = [] | |
220 | _pps = [] | |
221 | _download_retcode = None | |
222 | _num_downloads = None | |
223 | _screen_file = None | |
224 | ||
3511266b | 225 | def __init__(self, params=None, auto_init=True): |
8222d8de | 226 | """Create a FileDownloader object with the given options.""" |
e9f9a10f JMF |
227 | if params is None: |
228 | params = {} | |
8222d8de | 229 | self._ies = [] |
56c73665 | 230 | self._ies_instances = {} |
8222d8de | 231 | self._pps = [] |
933605d7 | 232 | self._progress_hooks = [] |
8222d8de JMF |
233 | self._download_retcode = 0 |
234 | self._num_downloads = 0 | |
235 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] | |
0783b09b | 236 | self._err_file = sys.stderr |
e9f9a10f | 237 | self.params = params |
a0e07d31 | 238 | self.cache = Cache(self) |
34308b30 | 239 | |
0783b09b | 240 | if params.get('bidi_workaround', False): |
1c088fa8 PH |
241 | try: |
242 | import pty | |
243 | master, slave = pty.openpty() | |
244 | width = get_term_width() | |
245 | if width is None: | |
246 | width_args = [] | |
247 | else: | |
248 | width_args = ['-w', str(width)] | |
5d681e96 | 249 | sp_kwargs = dict( |
1c088fa8 PH |
250 | stdin=subprocess.PIPE, |
251 | stdout=slave, | |
252 | stderr=self._err_file) | |
5d681e96 PH |
253 | try: |
254 | self._output_process = subprocess.Popen( | |
255 | ['bidiv'] + width_args, **sp_kwargs | |
256 | ) | |
257 | except OSError: | |
5d681e96 PH |
258 | self._output_process = subprocess.Popen( |
259 | ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) | |
260 | self._output_channel = os.fdopen(master, 'rb') | |
1c088fa8 PH |
261 | except OSError as ose: |
262 | if ose.errno == 2: | |
6febd1c1 | 263 | 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 $PATH.') |
1c088fa8 PH |
264 | else: |
265 | raise | |
0783b09b | 266 | |
34308b30 PH |
267 | if (sys.version_info >= (3,) and sys.platform != 'win32' and |
268 | sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] | |
53d9009b | 269 | and not params.get('restrictfilenames', False)): |
34308b30 PH |
270 | # On Python 3, the Unicode filesystem API will throw errors (#1474) |
271 | self.report_warning( | |
6febd1c1 | 272 | 'Assuming --restrict-filenames since file system encoding ' |
1b725173 | 273 | 'cannot encode all characters. ' |
6febd1c1 | 274 | 'Set the LC_ALL environment variable to fix this.') |
4a98cdbf | 275 | self.params['restrictfilenames'] = True |
34308b30 | 276 | |
a3927cf7 | 277 | if '%(stitle)s' in self.params.get('outtmpl', ''): |
6febd1c1 | 278 | self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') |
8222d8de | 279 | |
dca08720 PH |
280 | self._setup_opener() |
281 | ||
3511266b PH |
282 | if auto_init: |
283 | self.print_debug_header() | |
284 | self.add_default_info_extractors() | |
285 | ||
4f026faf PH |
286 | for pp_def_raw in self.params.get('postprocessors', []): |
287 | pp_class = get_postprocessor(pp_def_raw['key']) | |
288 | pp_def = dict(pp_def_raw) | |
289 | del pp_def['key'] | |
290 | pp = pp_class(self, **compat_kwargs(pp_def)) | |
291 | self.add_post_processor(pp) | |
292 | ||
71b640cc PH |
293 | for ph in self.params.get('progress_hooks', []): |
294 | self.add_progress_hook(ph) | |
295 | ||
7d4111ed PH |
296 | def warn_if_short_id(self, argv): |
297 | # short YouTube ID starting with dash? | |
298 | idxs = [ | |
299 | i for i, a in enumerate(argv) | |
300 | if re.match(r'^-[0-9A-Za-z_-]{10}$', a)] | |
301 | if idxs: | |
302 | correct_argv = ( | |
303 | ['youtube-dl'] + | |
304 | [a for i, a in enumerate(argv) if i not in idxs] + | |
305 | ['--'] + [argv[i] for i in idxs] | |
306 | ) | |
307 | self.report_warning( | |
308 | 'Long argument string detected. ' | |
309 | 'Use -- to separate parameters and URLs, like this:\n%s\n' % | |
310 | args_to_str(correct_argv)) | |
311 | ||
8222d8de JMF |
312 | def add_info_extractor(self, ie): |
313 | """Add an InfoExtractor object to the end of the list.""" | |
314 | self._ies.append(ie) | |
56c73665 | 315 | self._ies_instances[ie.ie_key()] = ie |
8222d8de JMF |
316 | ie.set_downloader(self) |
317 | ||
56c73665 JMF |
318 | def get_info_extractor(self, ie_key): |
319 | """ | |
320 | Get an instance of an IE with name ie_key, it will try to get one from | |
321 | the _ies list, if there's no instance it will create a new one and add | |
322 | it to the extractor list. | |
323 | """ | |
324 | ie = self._ies_instances.get(ie_key) | |
325 | if ie is None: | |
326 | ie = get_info_extractor(ie_key)() | |
327 | self.add_info_extractor(ie) | |
328 | return ie | |
329 | ||
023fa8c4 JMF |
330 | def add_default_info_extractors(self): |
331 | """ | |
332 | Add the InfoExtractors returned by gen_extractors to the end of the list | |
333 | """ | |
334 | for ie in gen_extractors(): | |
335 | self.add_info_extractor(ie) | |
336 | ||
8222d8de JMF |
337 | def add_post_processor(self, pp): |
338 | """Add a PostProcessor object to the end of the chain.""" | |
339 | self._pps.append(pp) | |
340 | pp.set_downloader(self) | |
341 | ||
933605d7 JMF |
342 | def add_progress_hook(self, ph): |
343 | """Add the progress hook (currently only for the file downloader)""" | |
344 | self._progress_hooks.append(ph) | |
8ab470f1 | 345 | |
1c088fa8 | 346 | def _bidi_workaround(self, message): |
5d681e96 | 347 | if not hasattr(self, '_output_channel'): |
1c088fa8 PH |
348 | return message |
349 | ||
5d681e96 | 350 | assert hasattr(self, '_output_process') |
11b85ce6 | 351 | assert isinstance(message, compat_str) |
6febd1c1 PH |
352 | line_count = message.count('\n') + 1 |
353 | self._output_process.stdin.write((message + '\n').encode('utf-8')) | |
5d681e96 | 354 | self._output_process.stdin.flush() |
6febd1c1 | 355 | res = ''.join(self._output_channel.readline().decode('utf-8') |
9e1a5b84 | 356 | for _ in range(line_count)) |
6febd1c1 | 357 | return res[:-len('\n')] |
1c088fa8 | 358 | |
8222d8de | 359 | def to_screen(self, message, skip_eol=False): |
0783b09b PH |
360 | """Print message to stdout if not in quiet mode.""" |
361 | return self.to_stdout(message, skip_eol, check_quiet=True) | |
362 | ||
734f90bb | 363 | def _write_string(self, s, out=None): |
b58ddb32 | 364 | write_string(s, out=out, encoding=self.params.get('encoding')) |
734f90bb | 365 | |
0783b09b | 366 | def to_stdout(self, message, skip_eol=False, check_quiet=False): |
8222d8de | 367 | """Print message to stdout if not in quiet mode.""" |
8bf9319e | 368 | if self.params.get('logger'): |
43afe285 | 369 | self.params['logger'].debug(message) |
0783b09b | 370 | elif not check_quiet or not self.params.get('quiet', False): |
1c088fa8 | 371 | message = self._bidi_workaround(message) |
6febd1c1 | 372 | terminator = ['\n', ''][skip_eol] |
8222d8de | 373 | output = message + terminator |
1c088fa8 | 374 | |
734f90bb | 375 | self._write_string(output, self._screen_file) |
8222d8de JMF |
376 | |
377 | def to_stderr(self, message): | |
378 | """Print message to stderr.""" | |
11b85ce6 | 379 | assert isinstance(message, compat_str) |
8bf9319e | 380 | if self.params.get('logger'): |
43afe285 IB |
381 | self.params['logger'].error(message) |
382 | else: | |
1c088fa8 | 383 | message = self._bidi_workaround(message) |
6febd1c1 | 384 | output = message + '\n' |
734f90bb | 385 | self._write_string(output, self._err_file) |
8222d8de | 386 | |
1e5b9a95 PH |
387 | def to_console_title(self, message): |
388 | if not self.params.get('consoletitle', False): | |
389 | return | |
390 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
391 | # c_wchar_p() might not be necessary if `message` is | |
392 | # already of type unicode() | |
393 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
394 | elif 'TERM' in os.environ: | |
734f90bb | 395 | self._write_string('\033]0;%s\007' % message, self._screen_file) |
1e5b9a95 | 396 | |
bdde425c PH |
397 | def save_console_title(self): |
398 | if not self.params.get('consoletitle', False): | |
399 | return | |
400 | if 'TERM' in os.environ: | |
efd6c574 | 401 | # Save the title on stack |
734f90bb | 402 | self._write_string('\033[22;0t', self._screen_file) |
bdde425c PH |
403 | |
404 | def restore_console_title(self): | |
405 | if not self.params.get('consoletitle', False): | |
406 | return | |
407 | if 'TERM' in os.environ: | |
efd6c574 | 408 | # Restore the title from stack |
734f90bb | 409 | self._write_string('\033[23;0t', self._screen_file) |
bdde425c PH |
410 | |
411 | def __enter__(self): | |
412 | self.save_console_title() | |
413 | return self | |
414 | ||
415 | def __exit__(self, *args): | |
416 | self.restore_console_title() | |
f89197d7 | 417 | |
dca08720 PH |
418 | if self.params.get('cookiefile') is not None: |
419 | self.cookiejar.save() | |
bdde425c | 420 | |
8222d8de JMF |
421 | def trouble(self, message=None, tb=None): |
422 | """Determine action to take when a download problem appears. | |
423 | ||
424 | Depending on if the downloader has been configured to ignore | |
425 | download errors or not, this method may throw an exception or | |
426 | not when errors are found, after printing the message. | |
427 | ||
428 | tb, if given, is additional traceback information. | |
429 | """ | |
430 | if message is not None: | |
431 | self.to_stderr(message) | |
432 | if self.params.get('verbose'): | |
433 | if tb is None: | |
434 | if sys.exc_info()[0]: # if .trouble has been called from an except block | |
6febd1c1 | 435 | tb = '' |
8222d8de | 436 | if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: |
6febd1c1 | 437 | tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) |
8222d8de JMF |
438 | tb += compat_str(traceback.format_exc()) |
439 | else: | |
440 | tb_data = traceback.format_list(traceback.extract_stack()) | |
6febd1c1 | 441 | tb = ''.join(tb_data) |
8222d8de JMF |
442 | self.to_stderr(tb) |
443 | if not self.params.get('ignoreerrors', False): | |
444 | if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: | |
445 | exc_info = sys.exc_info()[1].exc_info | |
446 | else: | |
447 | exc_info = sys.exc_info() | |
448 | raise DownloadError(message, exc_info) | |
449 | self._download_retcode = 1 | |
450 | ||
451 | def report_warning(self, message): | |
452 | ''' | |
453 | Print the message to stderr, it will be prefixed with 'WARNING:' | |
454 | If stderr is a tty file the 'WARNING:' will be colored | |
455 | ''' | |
6d07ce01 JMF |
456 | if self.params.get('logger') is not None: |
457 | self.params['logger'].warning(message) | |
8222d8de | 458 | else: |
ad8915b7 PH |
459 | if self.params.get('no_warnings'): |
460 | return | |
6d07ce01 JMF |
461 | if self._err_file.isatty() and os.name != 'nt': |
462 | _msg_header = '\033[0;33mWARNING:\033[0m' | |
463 | else: | |
464 | _msg_header = 'WARNING:' | |
465 | warning_message = '%s %s' % (_msg_header, message) | |
466 | self.to_stderr(warning_message) | |
8222d8de JMF |
467 | |
468 | def report_error(self, message, tb=None): | |
469 | ''' | |
470 | Do the same as trouble, but prefixes the message with 'ERROR:', colored | |
471 | in red if stderr is a tty file. | |
472 | ''' | |
0783b09b | 473 | if self._err_file.isatty() and os.name != 'nt': |
6febd1c1 | 474 | _msg_header = '\033[0;31mERROR:\033[0m' |
8222d8de | 475 | else: |
6febd1c1 PH |
476 | _msg_header = 'ERROR:' |
477 | error_message = '%s %s' % (_msg_header, message) | |
8222d8de JMF |
478 | self.trouble(error_message, tb) |
479 | ||
8222d8de JMF |
480 | def report_file_already_downloaded(self, file_name): |
481 | """Report file has already been fully downloaded.""" | |
482 | try: | |
6febd1c1 | 483 | self.to_screen('[download] %s has already been downloaded' % file_name) |
ce02ed60 | 484 | except UnicodeEncodeError: |
6febd1c1 | 485 | self.to_screen('[download] The file has already been downloaded') |
8222d8de | 486 | |
8222d8de JMF |
487 | def prepare_filename(self, info_dict): |
488 | """Generate the output filename.""" | |
489 | try: | |
490 | template_dict = dict(info_dict) | |
491 | ||
492 | template_dict['epoch'] = int(time.time()) | |
493 | autonumber_size = self.params.get('autonumber_size') | |
494 | if autonumber_size is None: | |
495 | autonumber_size = 5 | |
6febd1c1 | 496 | autonumber_templ = '%0' + str(autonumber_size) + 'd' |
8222d8de | 497 | template_dict['autonumber'] = autonumber_templ % self._num_downloads |
702665c0 | 498 | if template_dict.get('playlist_index') is not None: |
c6b4132a | 499 | template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index']) |
17b75c0d PH |
500 | if template_dict.get('resolution') is None: |
501 | if template_dict.get('width') and template_dict.get('height'): | |
502 | template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height']) | |
503 | elif template_dict.get('height'): | |
805ef3c6 | 504 | template_dict['resolution'] = '%sp' % template_dict['height'] |
17b75c0d | 505 | elif template_dict.get('width'): |
805ef3c6 | 506 | template_dict['resolution'] = '?x%d' % template_dict['width'] |
8222d8de | 507 | |
586a91b6 | 508 | sanitize = lambda k, v: sanitize_filename( |
45598aab | 509 | compat_str(v), |
8222d8de | 510 | restricted=self.params.get('restrictfilenames'), |
6febd1c1 | 511 | is_id=(k == 'id')) |
586a91b6 | 512 | template_dict = dict((k, sanitize(k, v)) |
45598aab PH |
513 | for k, v in template_dict.items() |
514 | if v is not None) | |
6febd1c1 | 515 | template_dict = collections.defaultdict(lambda: 'NA', template_dict) |
8222d8de | 516 | |
acd69589 | 517 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
4644ac55 | 518 | tmpl = compat_expanduser(outtmpl) |
586a91b6 | 519 | filename = tmpl % template_dict |
8222d8de | 520 | return filename |
8222d8de | 521 | except ValueError as err: |
6febd1c1 | 522 | self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') |
8222d8de JMF |
523 | return None |
524 | ||
525 | def _match_entry(self, info_dict): | |
526 | """ Returns None iff the file should be downloaded """ | |
527 | ||
6febd1c1 | 528 | video_title = info_dict.get('title', info_dict.get('id', 'video')) |
7012b23c PH |
529 | if 'title' in info_dict: |
530 | # This can happen when we're just evaluating the playlist | |
531 | title = info_dict['title'] | |
532 | matchtitle = self.params.get('matchtitle', False) | |
533 | if matchtitle: | |
534 | if not re.search(matchtitle, title, re.IGNORECASE): | |
6febd1c1 | 535 | return '"' + title + '" title did not match pattern "' + matchtitle + '"' |
7012b23c PH |
536 | rejecttitle = self.params.get('rejecttitle', False) |
537 | if rejecttitle: | |
538 | if re.search(rejecttitle, title, re.IGNORECASE): | |
6febd1c1 | 539 | return '"' + title + '" title matched reject pattern "' + rejecttitle + '"' |
8222d8de JMF |
540 | date = info_dict.get('upload_date', None) |
541 | if date is not None: | |
542 | dateRange = self.params.get('daterange', DateRange()) | |
543 | if date not in dateRange: | |
6febd1c1 | 544 | return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) |
5fe18bdb PH |
545 | view_count = info_dict.get('view_count', None) |
546 | if view_count is not None: | |
547 | min_views = self.params.get('min_views') | |
548 | if min_views is not None and view_count < min_views: | |
6febd1c1 | 549 | return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views) |
5fe18bdb PH |
550 | max_views = self.params.get('max_views') |
551 | if max_views is not None and view_count > max_views: | |
6febd1c1 | 552 | return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) |
8dbe9899 PH |
553 | age_limit = self.params.get('age_limit') |
554 | if age_limit is not None: | |
be843678 PH |
555 | actual_age_limit = info_dict.get('age_limit') |
556 | if actual_age_limit is None: | |
557 | actual_age_limit = 0 | |
558 | if age_limit < actual_age_limit: | |
6febd1c1 | 559 | return 'Skipping "' + title + '" because it is age restricted' |
c1c9a79c | 560 | if self.in_download_archive(info_dict): |
6febd1c1 | 561 | return '%s has already been recorded in archive' % video_title |
8222d8de | 562 | return None |
fe7e0c98 | 563 | |
b6c45014 JMF |
564 | @staticmethod |
565 | def add_extra_info(info_dict, extra_info): | |
566 | '''Set the keys from extra_info in info dict if they are missing''' | |
567 | for key, value in extra_info.items(): | |
568 | info_dict.setdefault(key, value) | |
569 | ||
7fc3fa05 PH |
570 | def extract_info(self, url, download=True, ie_key=None, extra_info={}, |
571 | process=True): | |
8222d8de JMF |
572 | ''' |
573 | Returns a list with a dictionary for each video we find. | |
574 | If 'download', also downloads the videos. | |
575 | extra_info is a dict containing the extra values to add to each result | |
576 | ''' | |
fe7e0c98 | 577 | |
8222d8de | 578 | if ie_key: |
56c73665 | 579 | ies = [self.get_info_extractor(ie_key)] |
8222d8de JMF |
580 | else: |
581 | ies = self._ies | |
582 | ||
583 | for ie in ies: | |
584 | if not ie.suitable(url): | |
585 | continue | |
586 | ||
587 | if not ie.working(): | |
6febd1c1 PH |
588 | self.report_warning('The program functionality for this site has been marked as broken, ' |
589 | 'and will probably not work.') | |
8222d8de JMF |
590 | |
591 | try: | |
592 | ie_result = ie.extract(url) | |
5f6a1245 | 593 | if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) |
8222d8de JMF |
594 | break |
595 | if isinstance(ie_result, list): | |
596 | # Backwards compatibility: old IE result format | |
8222d8de JMF |
597 | ie_result = { |
598 | '_type': 'compat_list', | |
599 | 'entries': ie_result, | |
600 | } | |
ea38e55f | 601 | self.add_default_extra_info(ie_result, ie, url) |
7fc3fa05 PH |
602 | if process: |
603 | return self.process_ie_result(ie_result, download, extra_info) | |
604 | else: | |
605 | return ie_result | |
5f6a1245 | 606 | except ExtractorError as de: # An error we somewhat expected |
8222d8de JMF |
607 | self.report_error(compat_str(de), de.format_traceback()) |
608 | break | |
d3e5bbf4 PH |
609 | except MaxDownloadsReached: |
610 | raise | |
8222d8de JMF |
611 | except Exception as e: |
612 | if self.params.get('ignoreerrors', False): | |
613 | self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) | |
614 | break | |
615 | else: | |
616 | raise | |
617 | else: | |
1a489545 | 618 | self.report_error('no suitable InfoExtractor for URL %s' % url) |
fe7e0c98 | 619 | |
ea38e55f PH |
620 | def add_default_extra_info(self, ie_result, ie, url): |
621 | self.add_extra_info(ie_result, { | |
622 | 'extractor': ie.IE_NAME, | |
623 | 'webpage_url': url, | |
624 | 'webpage_url_basename': url_basename(url), | |
625 | 'extractor_key': ie.ie_key(), | |
626 | }) | |
627 | ||
8222d8de JMF |
628 | def process_ie_result(self, ie_result, download=True, extra_info={}): |
629 | """ | |
630 | Take the result of the ie(may be modified) and resolve all unresolved | |
631 | references (URLs, playlist items). | |
632 | ||
633 | It will also download the videos if 'download'. | |
634 | Returns the resolved ie_result. | |
635 | """ | |
636 | ||
e8ee972c PH |
637 | result_type = ie_result.get('_type', 'video') |
638 | ||
057a5206 PH |
639 | if result_type in ('url', 'url_transparent'): |
640 | extract_flat = self.params.get('extract_flat', False) | |
641 | if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or | |
642 | extract_flat is True): | |
057a5206 PH |
643 | if self.params.get('forcejson', False): |
644 | self.to_stdout(json.dumps(ie_result)) | |
e8ee972c PH |
645 | return ie_result |
646 | ||
8222d8de | 647 | if result_type == 'video': |
b6c45014 | 648 | self.add_extra_info(ie_result, extra_info) |
feee2ecf | 649 | return self.process_video_result(ie_result, download=download) |
8222d8de JMF |
650 | elif result_type == 'url': |
651 | # We have to add extra_info to the results because it may be | |
652 | # contained in a playlist | |
653 | return self.extract_info(ie_result['url'], | |
654 | download, | |
655 | ie_key=ie_result.get('ie_key'), | |
656 | extra_info=extra_info) | |
7fc3fa05 PH |
657 | elif result_type == 'url_transparent': |
658 | # Use the information from the embedding page | |
659 | info = self.extract_info( | |
660 | ie_result['url'], ie_key=ie_result.get('ie_key'), | |
661 | extra_info=extra_info, download=False, process=False) | |
662 | ||
412c617d PH |
663 | force_properties = dict( |
664 | (k, v) for k, v in ie_result.items() if v is not None) | |
665 | for f in ('_type', 'url'): | |
666 | if f in force_properties: | |
667 | del force_properties[f] | |
668 | new_result = info.copy() | |
669 | new_result.update(force_properties) | |
7fc3fa05 PH |
670 | |
671 | assert new_result.get('_type') != 'url_transparent' | |
7fc3fa05 PH |
672 | |
673 | return self.process_ie_result( | |
674 | new_result, download=download, extra_info=extra_info) | |
42e12102 | 675 | elif result_type == 'playlist' or result_type == 'multi_video': |
8222d8de JMF |
676 | # We process each entry in the playlist |
677 | playlist = ie_result.get('title', None) or ie_result.get('id', None) | |
6febd1c1 | 678 | self.to_screen('[download] Downloading playlist: %s' % playlist) |
8222d8de JMF |
679 | |
680 | playlist_results = [] | |
681 | ||
8222d8de | 682 | playliststart = self.params.get('playliststart', 1) - 1 |
a19fd00c PH |
683 | playlistend = self.params.get('playlistend', None) |
684 | # For backwards compatibility, interpret -1 as whole list | |
8222d8de | 685 | if playlistend == -1: |
a19fd00c | 686 | playlistend = None |
8222d8de | 687 | |
b82f815f PH |
688 | ie_entries = ie_result['entries'] |
689 | if isinstance(ie_entries, list): | |
690 | n_all_entries = len(ie_entries) | |
691 | entries = ie_entries[playliststart:playlistend] | |
b7ab0590 PH |
692 | n_entries = len(entries) |
693 | self.to_screen( | |
694 | "[%s] playlist %s: Collected %d video ids (downloading %d of them)" % | |
695 | (ie_result['extractor'], playlist, n_all_entries, n_entries)) | |
b82f815f PH |
696 | elif isinstance(ie_entries, PagedList): |
697 | entries = ie_entries.getslice( | |
b7ab0590 PH |
698 | playliststart, playlistend) |
699 | n_entries = len(entries) | |
700 | self.to_screen( | |
701 | "[%s] playlist %s: Downloading %d videos" % | |
702 | (ie_result['extractor'], playlist, n_entries)) | |
b82f815f PH |
703 | else: # iterable |
704 | entries = list(itertools.islice( | |
705 | ie_entries, playliststart, playlistend)) | |
706 | n_entries = len(entries) | |
707 | self.to_screen( | |
708 | "[%s] playlist %s: Downloading %d videos" % | |
709 | (ie_result['extractor'], playlist, n_entries)) | |
8222d8de | 710 | |
ff815fe6 MS |
711 | if self.params.get('playlistreverse', False): |
712 | entries = entries[::-1] | |
713 | ||
fe7e0c98 | 714 | for i, entry in enumerate(entries, 1): |
734ea11e | 715 | self.to_screen('[download] Downloading video %s of %s' % (i, n_entries)) |
8222d8de | 716 | extra = { |
c6b4132a | 717 | 'n_entries': n_entries, |
fe7e0c98 | 718 | 'playlist': playlist, |
a1cf99d0 PH |
719 | 'playlist_id': ie_result.get('id'), |
720 | 'playlist_title': ie_result.get('title'), | |
fe7e0c98 | 721 | 'playlist_index': i + playliststart, |
b6c45014 | 722 | 'extractor': ie_result['extractor'], |
9103bbc5 | 723 | 'webpage_url': ie_result['webpage_url'], |
29eb5174 | 724 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 725 | 'extractor_key': ie_result['extractor_key'], |
fe7e0c98 | 726 | } |
7012b23c PH |
727 | |
728 | reason = self._match_entry(entry) | |
729 | if reason is not None: | |
6febd1c1 | 730 | self.to_screen('[download] ' + reason) |
7012b23c PH |
731 | continue |
732 | ||
8222d8de JMF |
733 | entry_result = self.process_ie_result(entry, |
734 | download=download, | |
735 | extra_info=extra) | |
736 | playlist_results.append(entry_result) | |
737 | ie_result['entries'] = playlist_results | |
738 | return ie_result | |
739 | elif result_type == 'compat_list': | |
c9bf4114 PH |
740 | self.report_warning( |
741 | 'Extractor %s returned a compat_list result. ' | |
742 | 'It needs to be updated.' % ie_result.get('extractor')) | |
5f6a1245 | 743 | |
8222d8de | 744 | def _fixup(r): |
9e1a5b84 JW |
745 | self.add_extra_info( |
746 | r, | |
9103bbc5 JMF |
747 | { |
748 | 'extractor': ie_result['extractor'], | |
749 | 'webpage_url': ie_result['webpage_url'], | |
29eb5174 | 750 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 751 | 'extractor_key': ie_result['extractor_key'], |
9e1a5b84 JW |
752 | } |
753 | ) | |
8222d8de JMF |
754 | return r |
755 | ie_result['entries'] = [ | |
b6c45014 | 756 | self.process_ie_result(_fixup(r), download, extra_info) |
8222d8de JMF |
757 | for r in ie_result['entries'] |
758 | ] | |
759 | return ie_result | |
760 | else: | |
761 | raise Exception('Invalid result type: %s' % result_type) | |
762 | ||
a9c58ad9 JMF |
763 | def select_format(self, format_spec, available_formats): |
764 | if format_spec == 'best' or format_spec is None: | |
765 | return available_formats[-1] | |
766 | elif format_spec == 'worst': | |
767 | return available_formats[0] | |
ba7678f9 PH |
768 | elif format_spec == 'bestaudio': |
769 | audio_formats = [ | |
770 | f for f in available_formats | |
771 | if f.get('vcodec') == 'none'] | |
772 | if audio_formats: | |
773 | return audio_formats[-1] | |
774 | elif format_spec == 'worstaudio': | |
775 | audio_formats = [ | |
776 | f for f in available_formats | |
777 | if f.get('vcodec') == 'none'] | |
778 | if audio_formats: | |
779 | return audio_formats[0] | |
bc6d5978 JMF |
780 | elif format_spec == 'bestvideo': |
781 | video_formats = [ | |
782 | f for f in available_formats | |
783 | if f.get('acodec') == 'none'] | |
784 | if video_formats: | |
785 | return video_formats[-1] | |
786 | elif format_spec == 'worstvideo': | |
787 | video_formats = [ | |
788 | f for f in available_formats | |
789 | if f.get('acodec') == 'none'] | |
790 | if video_formats: | |
791 | return video_formats[0] | |
a9c58ad9 | 792 | else: |
e2e5dae6 | 793 | extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a'] |
49e86983 JMF |
794 | if format_spec in extensions: |
795 | filter_f = lambda f: f['ext'] == format_spec | |
796 | else: | |
797 | filter_f = lambda f: f['format_id'] == format_spec | |
fe7e0c98 | 798 | matches = list(filter(filter_f, available_formats)) |
a9c58ad9 JMF |
799 | if matches: |
800 | return matches[-1] | |
801 | return None | |
802 | ||
dd82ffea JMF |
803 | def process_video_result(self, info_dict, download=True): |
804 | assert info_dict.get('_type', 'video') == 'video' | |
805 | ||
bec1fad2 PH |
806 | if 'id' not in info_dict: |
807 | raise ExtractorError('Missing "id" field in extractor result') | |
808 | if 'title' not in info_dict: | |
809 | raise ExtractorError('Missing "title" field in extractor result') | |
810 | ||
dd82ffea JMF |
811 | if 'playlist' not in info_dict: |
812 | # It isn't part of a playlist | |
813 | info_dict['playlist'] = None | |
814 | info_dict['playlist_index'] = None | |
815 | ||
d5519808 PH |
816 | thumbnails = info_dict.get('thumbnails') |
817 | if thumbnails: | |
be6d7229 PH |
818 | thumbnails.sort(key=lambda t: ( |
819 | t.get('width'), t.get('height'), t.get('url'))) | |
d5519808 PH |
820 | for t in thumbnails: |
821 | if 'width' in t and 'height' in t: | |
822 | t['resolution'] = '%dx%d' % (t['width'], t['height']) | |
823 | ||
824 | if thumbnails and 'thumbnail' not in info_dict: | |
825 | info_dict['thumbnail'] = thumbnails[-1]['url'] | |
826 | ||
c9ae7b95 | 827 | if 'display_id' not in info_dict and 'id' in info_dict: |
0afef30b PH |
828 | info_dict['display_id'] = info_dict['id'] |
829 | ||
955c4514 | 830 | if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None: |
706d7d4e S |
831 | # Working around negative timestamps in Windows |
832 | # (see http://bugs.python.org/issue1646728) | |
833 | if info_dict['timestamp'] < 0 and os.name == 'nt': | |
834 | info_dict['timestamp'] = 0 | |
9d2ecdbc | 835 | upload_date = datetime.datetime.utcfromtimestamp( |
955c4514 | 836 | info_dict['timestamp']) |
9d2ecdbc PH |
837 | info_dict['upload_date'] = upload_date.strftime('%Y%m%d') |
838 | ||
6ff000b8 | 839 | # This extractors handle format selection themselves |
6febd1c1 | 840 | if info_dict['extractor'] in ['Youku']: |
12893efe JMF |
841 | if download: |
842 | self.process_info(info_dict) | |
6ff000b8 JMF |
843 | return info_dict |
844 | ||
dd82ffea JMF |
845 | # We now pick which formats have to be downloaded |
846 | if info_dict.get('formats') is None: | |
847 | # There's only one format available | |
848 | formats = [info_dict] | |
849 | else: | |
850 | formats = info_dict['formats'] | |
851 | ||
db95dc13 PH |
852 | if not formats: |
853 | raise ExtractorError('No video formats found!') | |
854 | ||
dd82ffea | 855 | # We check that all the formats have the format and format_id fields |
db95dc13 | 856 | for i, format in enumerate(formats): |
bec1fad2 PH |
857 | if 'url' not in format: |
858 | raise ExtractorError('Missing "url" key in result (index %d)' % i) | |
859 | ||
dd82ffea | 860 | if format.get('format_id') is None: |
8016c922 | 861 | format['format_id'] = compat_str(i) |
8c51aa65 | 862 | if format.get('format') is None: |
6febd1c1 | 863 | format['format'] = '{id} - {res}{note}'.format( |
8c51aa65 JMF |
864 | id=format['format_id'], |
865 | res=self.format_resolution(format), | |
6febd1c1 | 866 | note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', |
8c51aa65 | 867 | ) |
c1002e96 PH |
868 | # Automatically determine file extension if missing |
869 | if 'ext' not in format: | |
cce929ea | 870 | format['ext'] = determine_ext(format['url']).lower() |
dd82ffea | 871 | |
99e206d5 JMF |
872 | format_limit = self.params.get('format_limit', None) |
873 | if format_limit: | |
f4d96df0 PH |
874 | formats = list(takewhile_inclusive( |
875 | lambda f: f['format_id'] != format_limit, formats | |
876 | )) | |
4bcc7bd1 PH |
877 | |
878 | # TODO Central sorting goes here | |
99e206d5 | 879 | |
f89197d7 | 880 | if formats[0] is not info_dict: |
b3d9ef88 JMF |
881 | # only set the 'formats' fields if the original info_dict list them |
882 | # otherwise we end up with a circular reference, the first (and unique) | |
f89197d7 | 883 | # element in the 'formats' field in info_dict is info_dict itself, |
b3d9ef88 JMF |
884 | # wich can't be exported to json |
885 | info_dict['formats'] = formats | |
bfaae0a7 | 886 | if self.params.get('listformats', None): |
887 | self.list_formats(info_dict) | |
888 | return | |
889 | ||
de3ef3ed | 890 | req_format = self.params.get('format') |
a9c58ad9 JMF |
891 | if req_format is None: |
892 | req_format = 'best' | |
dd82ffea | 893 | formats_to_download = [] |
dd82ffea | 894 | # The -1 is for supporting YoutubeIE |
a9c58ad9 | 895 | if req_format in ('-1', 'all'): |
dd82ffea JMF |
896 | formats_to_download = formats |
897 | else: | |
1de33faf PH |
898 | for rfstr in req_format.split(','): |
899 | # We can accept formats requested in the format: 34/5/best, we pick | |
900 | # the first that is available, starting from left | |
901 | req_formats = rfstr.split('/') | |
902 | for rf in req_formats: | |
903 | if re.match(r'.+?\+.+?', rf) is not None: | |
904 | # Two formats have been requested like '137+139' | |
905 | format_1, format_2 = rf.split('+') | |
906 | formats_info = (self.select_format(format_1, formats), | |
9e1a5b84 | 907 | self.select_format(format_2, formats)) |
1de33faf | 908 | if all(formats_info): |
c2954908 JMF |
909 | # The first format must contain the video and the |
910 | # second the audio | |
911 | if formats_info[0].get('vcodec') == 'none': | |
912 | self.report_error('The first format must ' | |
9e1a5b84 JW |
913 | 'contain the video, try using ' |
914 | '"-f %s+%s"' % (format_2, format_1)) | |
c2954908 | 915 | return |
1de33faf PH |
916 | selected_format = { |
917 | 'requested_formats': formats_info, | |
918 | 'format': rf, | |
919 | 'ext': formats_info[0]['ext'], | |
920 | } | |
921 | else: | |
922 | selected_format = None | |
6350728b | 923 | else: |
1de33faf PH |
924 | selected_format = self.select_format(rf, formats) |
925 | if selected_format is not None: | |
926 | formats_to_download.append(selected_format) | |
927 | break | |
dd82ffea | 928 | if not formats_to_download: |
6febd1c1 | 929 | raise ExtractorError('requested format not available', |
78a3a9f8 | 930 | expected=True) |
dd82ffea JMF |
931 | |
932 | if download: | |
933 | if len(formats_to_download) > 1: | |
6febd1c1 | 934 | self.to_screen('[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) |
dd82ffea JMF |
935 | for format in formats_to_download: |
936 | new_info = dict(info_dict) | |
937 | new_info.update(format) | |
938 | self.process_info(new_info) | |
939 | # We update the info dict with the best quality format (backwards compatibility) | |
940 | info_dict.update(formats_to_download[-1]) | |
941 | return info_dict | |
942 | ||
8222d8de JMF |
943 | def process_info(self, info_dict): |
944 | """Process a single resolved IE result.""" | |
945 | ||
946 | assert info_dict.get('_type', 'video') == 'video' | |
fd288278 PH |
947 | |
948 | max_downloads = self.params.get('max_downloads') | |
949 | if max_downloads is not None: | |
950 | if self._num_downloads >= int(max_downloads): | |
951 | raise MaxDownloadsReached() | |
8222d8de JMF |
952 | |
953 | info_dict['fulltitle'] = info_dict['title'] | |
954 | if len(info_dict['title']) > 200: | |
6febd1c1 | 955 | info_dict['title'] = info_dict['title'][:197] + '...' |
8222d8de JMF |
956 | |
957 | # Keep for backwards compatibility | |
958 | info_dict['stitle'] = info_dict['title'] | |
959 | ||
11b85ce6 | 960 | if 'format' not in info_dict: |
8222d8de JMF |
961 | info_dict['format'] = info_dict['ext'] |
962 | ||
963 | reason = self._match_entry(info_dict) | |
964 | if reason is not None: | |
6febd1c1 | 965 | self.to_screen('[download] ' + reason) |
8222d8de JMF |
966 | return |
967 | ||
fd288278 | 968 | self._num_downloads += 1 |
8222d8de JMF |
969 | |
970 | filename = self.prepare_filename(info_dict) | |
971 | ||
972 | # Forced printings | |
973 | if self.params.get('forcetitle', False): | |
0783b09b | 974 | self.to_stdout(info_dict['fulltitle']) |
8222d8de | 975 | if self.params.get('forceid', False): |
0783b09b | 976 | self.to_stdout(info_dict['id']) |
8222d8de | 977 | if self.params.get('forceurl', False): |
16ae61f6 | 978 | if info_dict.get('requested_formats') is not None: |
979 | for f in info_dict['requested_formats']: | |
980 | self.to_stdout(f['url'] + f.get('play_path', '')) | |
981 | else: | |
982 | # For RTMP URLs, also include the playpath | |
983 | self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) | |
216d71d0 | 984 | if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: |
0783b09b | 985 | self.to_stdout(info_dict['thumbnail']) |
216d71d0 | 986 | if self.params.get('forcedescription', False) and info_dict.get('description') is not None: |
0783b09b | 987 | self.to_stdout(info_dict['description']) |
8222d8de | 988 | if self.params.get('forcefilename', False) and filename is not None: |
0783b09b | 989 | self.to_stdout(filename) |
525ef922 PH |
990 | if self.params.get('forceduration', False) and info_dict.get('duration') is not None: |
991 | self.to_stdout(formatSeconds(info_dict['duration'])) | |
8222d8de | 992 | if self.params.get('forceformat', False): |
0783b09b | 993 | self.to_stdout(info_dict['format']) |
9d153818 | 994 | if self.params.get('forcejson', False): |
a0d96c98 | 995 | info_dict['_filename'] = filename |
0783b09b | 996 | self.to_stdout(json.dumps(info_dict)) |
63e0be34 PH |
997 | if self.params.get('dump_single_json', False): |
998 | info_dict['_filename'] = filename | |
8222d8de JMF |
999 | |
1000 | # Do nothing else if in simulate mode | |
1001 | if self.params.get('simulate', False): | |
1002 | return | |
1003 | ||
1004 | if filename is None: | |
1005 | return | |
1006 | ||
1007 | try: | |
1008 | dn = os.path.dirname(encodeFilename(filename)) | |
d26e981d | 1009 | if dn and not os.path.exists(dn): |
8222d8de JMF |
1010 | os.makedirs(dn) |
1011 | except (OSError, IOError) as err: | |
6febd1c1 | 1012 | self.report_error('unable to create directory ' + compat_str(err)) |
8222d8de JMF |
1013 | return |
1014 | ||
1015 | if self.params.get('writedescription', False): | |
6febd1c1 | 1016 | descfn = filename + '.description' |
7b6fefc9 | 1017 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): |
6febd1c1 | 1018 | self.to_screen('[info] Video description is already present') |
7b6fefc9 PH |
1019 | else: |
1020 | try: | |
6febd1c1 | 1021 | self.to_screen('[info] Writing video description to: ' + descfn) |
7b6fefc9 PH |
1022 | with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: |
1023 | descfile.write(info_dict['description']) | |
1024 | except (KeyError, TypeError): | |
6febd1c1 | 1025 | self.report_warning('There\'s no description to write.') |
7b6fefc9 | 1026 | except (OSError, IOError): |
6febd1c1 | 1027 | self.report_error('Cannot write description file ' + descfn) |
7b6fefc9 | 1028 | return |
8222d8de | 1029 | |
1fb07d10 | 1030 | if self.params.get('writeannotations', False): |
6febd1c1 | 1031 | annofn = filename + '.annotations.xml' |
7b6fefc9 | 1032 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): |
6febd1c1 | 1033 | self.to_screen('[info] Video annotations are already present') |
7b6fefc9 PH |
1034 | else: |
1035 | try: | |
6febd1c1 | 1036 | self.to_screen('[info] Writing video annotations to: ' + annofn) |
7b6fefc9 PH |
1037 | with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: |
1038 | annofile.write(info_dict['annotations']) | |
1039 | except (KeyError, TypeError): | |
6febd1c1 | 1040 | self.report_warning('There are no annotations to write.') |
7b6fefc9 | 1041 | except (OSError, IOError): |
6febd1c1 | 1042 | self.report_error('Cannot write annotations file: ' + annofn) |
7b6fefc9 | 1043 | return |
1fb07d10 | 1044 | |
c4a91be7 | 1045 | subtitles_are_requested = any([self.params.get('writesubtitles', False), |
0b7f3118 | 1046 | self.params.get('writeautomaticsub')]) |
c4a91be7 | 1047 | |
fe7e0c98 | 1048 | if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']: |
8222d8de JMF |
1049 | # subtitles download errors are already managed as troubles in relevant IE |
1050 | # that way it will silently go on when used with unsupporting IE | |
8222d8de | 1051 | subtitles = info_dict['subtitles'] |
ca715127 | 1052 | sub_format = self.params.get('subtitlesformat', 'srt') |
5d51a883 JMF |
1053 | for sub_lang in subtitles.keys(): |
1054 | sub = subtitles[sub_lang] | |
6804038d JMF |
1055 | if sub is None: |
1056 | continue | |
8222d8de | 1057 | try: |
d4051a8e | 1058 | sub_filename = subtitles_filename(filename, sub_lang, sub_format) |
7b6fefc9 | 1059 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): |
6febd1c1 | 1060 | self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) |
7b6fefc9 | 1061 | else: |
6febd1c1 | 1062 | self.to_screen('[info] Writing video subtitles to: ' + sub_filename) |
7b6fefc9 | 1063 | with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: |
5f6a1245 | 1064 | subfile.write(sub) |
8222d8de | 1065 | except (OSError, IOError): |
e4db1951 | 1066 | self.report_error('Cannot write subtitles file ' + sub_filename) |
8222d8de JMF |
1067 | return |
1068 | ||
8222d8de | 1069 | if self.params.get('writeinfojson', False): |
6febd1c1 | 1070 | infofn = os.path.splitext(filename)[0] + '.info.json' |
7b6fefc9 | 1071 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)): |
6febd1c1 | 1072 | self.to_screen('[info] Video description metadata is already present') |
7b6fefc9 | 1073 | else: |
6febd1c1 | 1074 | self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn) |
7b6fefc9 | 1075 | try: |
92120217 | 1076 | write_json_file(info_dict, infofn) |
7b6fefc9 | 1077 | except (OSError, IOError): |
6febd1c1 | 1078 | self.report_error('Cannot write metadata to JSON file ' + infofn) |
7b6fefc9 | 1079 | return |
8222d8de JMF |
1080 | |
1081 | if self.params.get('writethumbnail', False): | |
d8269e1d | 1082 | if info_dict.get('thumbnail') is not None: |
6febd1c1 PH |
1083 | thumb_format = determine_ext(info_dict['thumbnail'], 'jpg') |
1084 | thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format | |
0a9ce268 | 1085 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)): |
6febd1c1 | 1086 | self.to_screen('[%s] %s: Thumbnail is already present' % |
7b6fefc9 PH |
1087 | (info_dict['extractor'], info_dict['id'])) |
1088 | else: | |
6febd1c1 | 1089 | self.to_screen('[%s] %s: Downloading thumbnail ...' % |
7b6fefc9 PH |
1090 | (info_dict['extractor'], info_dict['id'])) |
1091 | try: | |
e9c092f1 | 1092 | uf = self.urlopen(info_dict['thumbnail']) |
7b6fefc9 PH |
1093 | with open(thumb_filename, 'wb') as thumbf: |
1094 | shutil.copyfileobj(uf, thumbf) | |
6febd1c1 | 1095 | self.to_screen('[%s] %s: Writing thumbnail to: %s' % |
9e1a5b84 | 1096 | (info_dict['extractor'], info_dict['id'], thumb_filename)) |
7b6fefc9 | 1097 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
6febd1c1 | 1098 | self.report_warning('Unable to download thumbnail "%s": %s' % |
9e1a5b84 | 1099 | (info_dict['thumbnail'], compat_str(err))) |
8222d8de JMF |
1100 | |
1101 | if not self.params.get('skip_download', False): | |
1102 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): | |
1103 | success = True | |
1104 | else: | |
1105 | try: | |
6350728b JMF |
1106 | def dl(name, info): |
1107 | fd = get_suitable_downloader(info)(self, self.params) | |
1108 | for ph in self._progress_hooks: | |
1109 | fd.add_progress_hook(ph) | |
8d5797b0 PH |
1110 | if self.params.get('verbose'): |
1111 | self.to_stdout('[debug] Invoking downloader on %r' % info.get('url')) | |
6350728b JMF |
1112 | return fd.download(name, info) |
1113 | if info_dict.get('requested_formats') is not None: | |
1114 | downloaded = [] | |
1115 | success = True | |
b7f81164 | 1116 | merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) |
48844745 | 1117 | if not merger._executable: |
58c3c7ae JMF |
1118 | postprocessors = [] |
1119 | self.report_warning('You have requested multiple ' | |
9e1a5b84 JW |
1120 | 'formats but ffmpeg or avconv are not installed.' |
1121 | ' The formats won\'t be merged') | |
58c3c7ae JMF |
1122 | else: |
1123 | postprocessors = [merger] | |
6350728b JMF |
1124 | for f in info_dict['requested_formats']: |
1125 | new_info = dict(info_dict) | |
1126 | new_info.update(f) | |
1127 | fname = self.prepare_filename(new_info) | |
1128 | fname = prepend_extension(fname, 'f%s' % f['format_id']) | |
1129 | downloaded.append(fname) | |
1130 | partial_success = dl(fname, new_info) | |
1131 | success = success and partial_success | |
58c3c7ae | 1132 | info_dict['__postprocessors'] = postprocessors |
6350728b JMF |
1133 | info_dict['__files_to_merge'] = downloaded |
1134 | else: | |
1135 | # Just a single file | |
1136 | success = dl(filename, info_dict) | |
8222d8de | 1137 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
6febd1c1 | 1138 | self.report_error('unable to download video data: %s' % str(err)) |
8222d8de | 1139 | return |
c40c6aaa JMF |
1140 | except (OSError, IOError) as err: |
1141 | raise UnavailableVideoError(err) | |
8222d8de | 1142 | except (ContentTooShortError, ) as err: |
6febd1c1 | 1143 | self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) |
8222d8de JMF |
1144 | return |
1145 | ||
1146 | if success: | |
1147 | try: | |
1148 | self.post_process(filename, info_dict) | |
1149 | except (PostProcessingError) as err: | |
6febd1c1 | 1150 | self.report_error('postprocessing: %s' % str(err)) |
8222d8de | 1151 | return |
cd58dc3e | 1152 | self.record_download_archive(info_dict) |
8222d8de JMF |
1153 | |
1154 | def download(self, url_list): | |
1155 | """Download a given list of URLs.""" | |
acd69589 | 1156 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
0c75c3fa | 1157 | if (len(url_list) > 1 and |
acd69589 | 1158 | '%' not in outtmpl |
0c75c3fa | 1159 | and self.params.get('max_downloads') != 1): |
acd69589 | 1160 | raise SameFileError(outtmpl) |
8222d8de JMF |
1161 | |
1162 | for url in url_list: | |
1163 | try: | |
5f6a1245 | 1164 | # It also downloads the videos |
63e0be34 | 1165 | res = self.extract_info(url) |
8222d8de | 1166 | except UnavailableVideoError: |
6febd1c1 | 1167 | self.report_error('unable to download video') |
8222d8de | 1168 | except MaxDownloadsReached: |
6febd1c1 | 1169 | self.to_screen('[info] Maximum number of downloaded files reached.') |
8222d8de | 1170 | raise |
63e0be34 PH |
1171 | else: |
1172 | if self.params.get('dump_single_json', False): | |
1173 | self.to_stdout(json.dumps(res)) | |
8222d8de JMF |
1174 | |
1175 | return self._download_retcode | |
1176 | ||
1dcc4c0c | 1177 | def download_with_info_file(self, info_filename): |
395293a8 | 1178 | with io.open(info_filename, 'r', encoding='utf-8') as f: |
1dcc4c0c | 1179 | info = json.load(f) |
d4943898 JMF |
1180 | try: |
1181 | self.process_ie_result(info, download=True) | |
1182 | except DownloadError: | |
1183 | webpage_url = info.get('webpage_url') | |
1184 | if webpage_url is not None: | |
6febd1c1 | 1185 | self.report_warning('The info failed to download, trying with "%s"' % webpage_url) |
d4943898 JMF |
1186 | return self.download([webpage_url]) |
1187 | else: | |
1188 | raise | |
1189 | return self._download_retcode | |
1dcc4c0c | 1190 | |
8222d8de JMF |
1191 | def post_process(self, filename, ie_info): |
1192 | """Run all the postprocessors on the given file.""" | |
1193 | info = dict(ie_info) | |
1194 | info['filepath'] = filename | |
1195 | keep_video = None | |
6350728b JMF |
1196 | pps_chain = [] |
1197 | if ie_info.get('__postprocessors') is not None: | |
1198 | pps_chain.extend(ie_info['__postprocessors']) | |
1199 | pps_chain.extend(self._pps) | |
1200 | for pp in pps_chain: | |
8222d8de | 1201 | try: |
fe7e0c98 | 1202 | keep_video_wish, new_info = pp.run(info) |
8222d8de JMF |
1203 | if keep_video_wish is not None: |
1204 | if keep_video_wish: | |
1205 | keep_video = keep_video_wish | |
1206 | elif keep_video is None: | |
1207 | # No clear decision yet, let IE decide | |
1208 | keep_video = keep_video_wish | |
1209 | except PostProcessingError as e: | |
bbcbf4d4 | 1210 | self.report_error(e.msg) |
8222d8de JMF |
1211 | if keep_video is False and not self.params.get('keepvideo', False): |
1212 | try: | |
6febd1c1 | 1213 | self.to_screen('Deleting original file %s (pass -k to keep)' % filename) |
8222d8de JMF |
1214 | os.remove(encodeFilename(filename)) |
1215 | except (IOError, OSError): | |
6febd1c1 | 1216 | self.report_warning('Unable to remove downloaded video file') |
c1c9a79c | 1217 | |
5db07df6 PH |
1218 | def _make_archive_id(self, info_dict): |
1219 | # Future-proof against any change in case | |
1220 | # and backwards compatibility with prior versions | |
d31209a1 | 1221 | extractor = info_dict.get('extractor_key') |
7012b23c PH |
1222 | if extractor is None: |
1223 | if 'id' in info_dict: | |
1224 | extractor = info_dict.get('ie_key') # key in a playlist | |
1225 | if extractor is None: | |
5db07df6 | 1226 | return None # Incomplete video information |
6febd1c1 | 1227 | return extractor.lower() + ' ' + info_dict['id'] |
5db07df6 PH |
1228 | |
1229 | def in_download_archive(self, info_dict): | |
1230 | fn = self.params.get('download_archive') | |
1231 | if fn is None: | |
1232 | return False | |
1233 | ||
1234 | vid_id = self._make_archive_id(info_dict) | |
1235 | if vid_id is None: | |
7012b23c | 1236 | return False # Incomplete video information |
5db07df6 | 1237 | |
c1c9a79c PH |
1238 | try: |
1239 | with locked_file(fn, 'r', encoding='utf-8') as archive_file: | |
1240 | for line in archive_file: | |
1241 | if line.strip() == vid_id: | |
1242 | return True | |
1243 | except IOError as ioe: | |
1244 | if ioe.errno != errno.ENOENT: | |
1245 | raise | |
1246 | return False | |
1247 | ||
1248 | def record_download_archive(self, info_dict): | |
1249 | fn = self.params.get('download_archive') | |
1250 | if fn is None: | |
1251 | return | |
5db07df6 PH |
1252 | vid_id = self._make_archive_id(info_dict) |
1253 | assert vid_id | |
c1c9a79c | 1254 | with locked_file(fn, 'a', encoding='utf-8') as archive_file: |
6febd1c1 | 1255 | archive_file.write(vid_id + '\n') |
dd82ffea | 1256 | |
8c51aa65 | 1257 | @staticmethod |
8abeeb94 | 1258 | def format_resolution(format, default='unknown'): |
fb04e403 PH |
1259 | if format.get('vcodec') == 'none': |
1260 | return 'audio only' | |
f49d89ee PH |
1261 | if format.get('resolution') is not None: |
1262 | return format['resolution'] | |
8c51aa65 JMF |
1263 | if format.get('height') is not None: |
1264 | if format.get('width') is not None: | |
6febd1c1 | 1265 | res = '%sx%s' % (format['width'], format['height']) |
8c51aa65 | 1266 | else: |
6febd1c1 | 1267 | res = '%sp' % format['height'] |
f49d89ee | 1268 | elif format.get('width') is not None: |
6febd1c1 | 1269 | res = '?x%d' % format['width'] |
8c51aa65 | 1270 | else: |
8abeeb94 | 1271 | res = default |
8c51aa65 JMF |
1272 | return res |
1273 | ||
c57f7757 PH |
1274 | def _format_note(self, fdict): |
1275 | res = '' | |
1276 | if fdict.get('ext') in ['f4f', 'f4m']: | |
1277 | res += '(unsupported) ' | |
1278 | if fdict.get('format_note') is not None: | |
1279 | res += fdict['format_note'] + ' ' | |
1280 | if fdict.get('tbr') is not None: | |
1281 | res += '%4dk ' % fdict['tbr'] | |
1282 | if fdict.get('container') is not None: | |
1283 | if res: | |
1284 | res += ', ' | |
1285 | res += '%s container' % fdict['container'] | |
1286 | if (fdict.get('vcodec') is not None and | |
1287 | fdict.get('vcodec') != 'none'): | |
1288 | if res: | |
1289 | res += ', ' | |
1290 | res += fdict['vcodec'] | |
91c7271a | 1291 | if fdict.get('vbr') is not None: |
c57f7757 PH |
1292 | res += '@' |
1293 | elif fdict.get('vbr') is not None and fdict.get('abr') is not None: | |
1294 | res += 'video@' | |
1295 | if fdict.get('vbr') is not None: | |
1296 | res += '%4dk' % fdict['vbr'] | |
fbb21cf5 PH |
1297 | if fdict.get('fps') is not None: |
1298 | res += ', %sfps' % fdict['fps'] | |
c57f7757 PH |
1299 | if fdict.get('acodec') is not None: |
1300 | if res: | |
1301 | res += ', ' | |
1302 | if fdict['acodec'] == 'none': | |
1303 | res += 'video only' | |
1304 | else: | |
1305 | res += '%-5s' % fdict['acodec'] | |
1306 | elif fdict.get('abr') is not None: | |
1307 | if res: | |
1308 | res += ', ' | |
1309 | res += 'audio' | |
1310 | if fdict.get('abr') is not None: | |
1311 | res += '@%3dk' % fdict['abr'] | |
1312 | if fdict.get('asr') is not None: | |
1313 | res += ' (%5dHz)' % fdict['asr'] | |
1314 | if fdict.get('filesize') is not None: | |
1315 | if res: | |
1316 | res += ', ' | |
1317 | res += format_bytes(fdict['filesize']) | |
9732d77e PH |
1318 | elif fdict.get('filesize_approx') is not None: |
1319 | if res: | |
1320 | res += ', ' | |
1321 | res += '~' + format_bytes(fdict['filesize_approx']) | |
c57f7757 | 1322 | return res |
91c7271a | 1323 | |
c57f7757 | 1324 | def list_formats(self, info_dict): |
02dbf93f | 1325 | def line(format, idlen=20): |
6febd1c1 | 1326 | return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % ( |
8c51aa65 JMF |
1327 | format['format_id'], |
1328 | format['ext'], | |
8c51aa65 | 1329 | self.format_resolution(format), |
c57f7757 | 1330 | self._format_note(format), |
02dbf93f | 1331 | )) |
57dd9a8f | 1332 | |
94badb25 | 1333 | formats = info_dict.get('formats', [info_dict]) |
6febd1c1 | 1334 | idlen = max(len('format code'), |
02dbf93f PH |
1335 | max(len(f['format_id']) for f in formats)) |
1336 | formats_s = [line(f, idlen) for f in formats] | |
94badb25 | 1337 | if len(formats) > 1: |
c57f7757 PH |
1338 | formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)' |
1339 | formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)' | |
57dd9a8f PH |
1340 | |
1341 | header_line = line({ | |
6febd1c1 PH |
1342 | 'format_id': 'format code', 'ext': 'extension', |
1343 | 'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen) | |
1344 | self.to_screen('[info] Available formats for %s:\n%s\n%s' % | |
1345 | (info_dict['id'], header_line, '\n'.join(formats_s))) | |
dca08720 PH |
1346 | |
1347 | def urlopen(self, req): | |
1348 | """ Start an HTTP download """ | |
37419b4f | 1349 | |
d05cfe06 S |
1350 | # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not |
1351 | # always respected by websites, some tend to give out URLs with non percent-encoded | |
1352 | # non-ASCII characters (see telemb.py, ard.py [#3412]) | |
37419b4f | 1353 | # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991) |
d05cfe06 S |
1354 | # To work around aforementioned issue we will replace request's original URL with |
1355 | # percent-encoded one | |
ee0d9070 | 1356 | req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str) |
68b09730 | 1357 | url = req if req_is_string else req.get_full_url() |
d05cfe06 | 1358 | url_escaped = escape_url(url) |
37419b4f S |
1359 | |
1360 | # Substitute URL if any change after escaping | |
1361 | if url != url_escaped: | |
68b09730 | 1362 | if req_is_string: |
37419b4f S |
1363 | req = url_escaped |
1364 | else: | |
1365 | req = compat_urllib_request.Request( | |
1366 | url_escaped, data=req.data, headers=req.headers, | |
1367 | origin_req_host=req.origin_req_host, unverifiable=req.unverifiable) | |
1368 | ||
19a41fc6 | 1369 | return self._opener.open(req, timeout=self._socket_timeout) |
dca08720 PH |
1370 | |
1371 | def print_debug_header(self): | |
1372 | if not self.params.get('verbose'): | |
1373 | return | |
62fec3b2 | 1374 | |
4192b51c PH |
1375 | if type('') is not compat_str: |
1376 | # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326) | |
1377 | self.report_warning( | |
1378 | 'Your Python is broken! Update to a newer and supported version') | |
1379 | ||
c6afed48 PH |
1380 | stdout_encoding = getattr( |
1381 | sys.stdout, 'encoding', 'missing (%s)' % type(sys.stdout).__name__) | |
b0472057 | 1382 | encoding_str = ( |
734f90bb PH |
1383 | '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( |
1384 | locale.getpreferredencoding(), | |
1385 | sys.getfilesystemencoding(), | |
c6afed48 | 1386 | stdout_encoding, |
b0472057 | 1387 | self.get_encoding())) |
4192b51c | 1388 | write_string(encoding_str, encoding=None) |
734f90bb PH |
1389 | |
1390 | self._write_string('[debug] youtube-dl version ' + __version__ + '\n') | |
dca08720 PH |
1391 | try: |
1392 | sp = subprocess.Popen( | |
1393 | ['git', 'rev-parse', '--short', 'HEAD'], | |
1394 | stdout=subprocess.PIPE, stderr=subprocess.PIPE, | |
1395 | cwd=os.path.dirname(os.path.abspath(__file__))) | |
1396 | out, err = sp.communicate() | |
1397 | out = out.decode().strip() | |
1398 | if re.match('[0-9a-f]+', out): | |
734f90bb | 1399 | self._write_string('[debug] Git HEAD: ' + out + '\n') |
dca08720 PH |
1400 | except: |
1401 | try: | |
1402 | sys.exc_clear() | |
1403 | except: | |
1404 | pass | |
d28b5171 PH |
1405 | self._write_string('[debug] Python version %s - %s\n' % ( |
1406 | platform.python_version(), platform_name())) | |
1407 | ||
1408 | exe_versions = FFmpegPostProcessor.get_versions() | |
4c83c967 | 1409 | exe_versions['rtmpdump'] = rtmpdump_version() |
d28b5171 PH |
1410 | exe_str = ', '.join( |
1411 | '%s %s' % (exe, v) | |
1412 | for exe, v in sorted(exe_versions.items()) | |
1413 | if v | |
1414 | ) | |
1415 | if not exe_str: | |
1416 | exe_str = 'none' | |
1417 | self._write_string('[debug] exe versions: %s\n' % exe_str) | |
dca08720 PH |
1418 | |
1419 | proxy_map = {} | |
1420 | for handler in self._opener.handlers: | |
1421 | if hasattr(handler, 'proxies'): | |
1422 | proxy_map.update(handler.proxies) | |
734f90bb | 1423 | self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') |
dca08720 | 1424 | |
e344693b | 1425 | def _setup_opener(self): |
6ad14cab | 1426 | timeout_val = self.params.get('socket_timeout') |
19a41fc6 | 1427 | self._socket_timeout = 600 if timeout_val is None else float(timeout_val) |
6ad14cab | 1428 | |
dca08720 PH |
1429 | opts_cookiefile = self.params.get('cookiefile') |
1430 | opts_proxy = self.params.get('proxy') | |
1431 | ||
1432 | if opts_cookiefile is None: | |
1433 | self.cookiejar = compat_cookiejar.CookieJar() | |
1434 | else: | |
1435 | self.cookiejar = compat_cookiejar.MozillaCookieJar( | |
1436 | opts_cookiefile) | |
1437 | if os.access(opts_cookiefile, os.R_OK): | |
1438 | self.cookiejar.load() | |
1439 | ||
1440 | cookie_processor = compat_urllib_request.HTTPCookieProcessor( | |
1441 | self.cookiejar) | |
1442 | if opts_proxy is not None: | |
1443 | if opts_proxy == '': | |
1444 | proxies = {} | |
1445 | else: | |
1446 | proxies = {'http': opts_proxy, 'https': opts_proxy} | |
1447 | else: | |
1448 | proxies = compat_urllib_request.getproxies() | |
1449 | # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) | |
1450 | if 'http' in proxies and 'https' not in proxies: | |
1451 | proxies['https'] = proxies['http'] | |
1452 | proxy_handler = compat_urllib_request.ProxyHandler(proxies) | |
a0ddb8a2 PH |
1453 | |
1454 | debuglevel = 1 if self.params.get('debug_printtraffic') else 0 | |
dca08720 | 1455 | https_handler = make_HTTPS_handler( |
a0ddb8a2 PH |
1456 | self.params.get('nocheckcertificate', False), debuglevel=debuglevel) |
1457 | ydlh = YoutubeDLHandler(debuglevel=debuglevel) | |
dca08720 | 1458 | opener = compat_urllib_request.build_opener( |
a0ddb8a2 | 1459 | https_handler, proxy_handler, cookie_processor, ydlh) |
dca08720 PH |
1460 | # Delete the default user-agent header, which would otherwise apply in |
1461 | # cases where our custom HTTP handler doesn't come into play | |
1462 | # (See https://github.com/rg3/youtube-dl/issues/1309 for details) | |
1463 | opener.addheaders = [] | |
1464 | self._opener = opener | |
62fec3b2 PH |
1465 | |
1466 | def encode(self, s): | |
1467 | if isinstance(s, bytes): | |
1468 | return s # Already encoded | |
1469 | ||
1470 | try: | |
1471 | return s.encode(self.get_encoding()) | |
1472 | except UnicodeEncodeError as err: | |
1473 | err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.' | |
1474 | raise | |
1475 | ||
1476 | def get_encoding(self): | |
1477 | encoding = self.params.get('encoding') | |
1478 | if encoding is None: | |
1479 | encoding = preferredencoding() | |
1480 | return encoding |