]>
Commit | Line | Data |
---|---|---|
8222d8de JMF |
1 | #!/usr/bin/env python |
2 | # -*- coding: utf-8 -*- | |
3 | ||
6febd1c1 | 4 | from __future__ import absolute_import, unicode_literals |
8222d8de | 5 | |
26e63931 | 6 | import collections |
9d2ecdbc | 7 | import datetime |
c1c9a79c | 8 | import errno |
8222d8de | 9 | import io |
8694c600 | 10 | import json |
62fec3b2 | 11 | import locale |
8222d8de | 12 | import os |
dca08720 | 13 | import platform |
8222d8de JMF |
14 | import re |
15 | import shutil | |
dca08720 | 16 | import subprocess |
8222d8de JMF |
17 | import socket |
18 | import sys | |
19 | import time | |
20 | import traceback | |
21 | ||
1e5b9a95 PH |
22 | if os.name == 'nt': |
23 | import ctypes | |
24 | ||
8c25f81b | 25 | from .compat import ( |
dca08720 | 26 | compat_cookiejar, |
4644ac55 | 27 | compat_expanduser, |
ce02ed60 | 28 | compat_http_client, |
ce02ed60 PH |
29 | compat_str, |
30 | compat_urllib_error, | |
31 | compat_urllib_request, | |
7d4111ed | 32 | shlex_quote, |
8c25f81b PH |
33 | ) |
34 | from .utils import ( | |
d05cfe06 | 35 | escape_url, |
ce02ed60 PH |
36 | ContentTooShortError, |
37 | date_from_str, | |
38 | DateRange, | |
acd69589 | 39 | DEFAULT_OUTTMPL, |
ce02ed60 PH |
40 | determine_ext, |
41 | DownloadError, | |
42 | encodeFilename, | |
43 | ExtractorError, | |
02dbf93f | 44 | format_bytes, |
525ef922 | 45 | formatSeconds, |
1c088fa8 | 46 | get_term_width, |
ce02ed60 | 47 | locked_file, |
dca08720 | 48 | make_HTTPS_handler, |
ce02ed60 | 49 | MaxDownloadsReached, |
b7ab0590 | 50 | PagedList, |
ce02ed60 | 51 | PostProcessingError, |
dca08720 | 52 | platform_name, |
ce02ed60 PH |
53 | preferredencoding, |
54 | SameFileError, | |
55 | sanitize_filename, | |
56 | subtitles_filename, | |
57 | takewhile_inclusive, | |
58 | UnavailableVideoError, | |
29eb5174 | 59 | url_basename, |
ce02ed60 PH |
60 | write_json_file, |
61 | write_string, | |
dca08720 | 62 | YoutubeDLHandler, |
6350728b | 63 | prepend_extension, |
7d4111ed | 64 | args_to_str, |
ce02ed60 | 65 | ) |
a0e07d31 | 66 | from .cache import Cache |
023fa8c4 | 67 | from .extractor import get_info_extractor, gen_extractors |
3bc2ddcc | 68 | from .downloader import get_suitable_downloader |
4c83c967 | 69 | from .downloader.rtmp import rtmpdump_version |
d28b5171 | 70 | from .postprocessor import FFmpegMergerPP, FFmpegPostProcessor |
dca08720 | 71 | from .version import __version__ |
8222d8de JMF |
72 | |
73 | ||
74 | class YoutubeDL(object): | |
75 | """YoutubeDL class. | |
76 | ||
77 | YoutubeDL objects are the ones responsible of downloading the | |
78 | actual video file and writing it to disk if the user has requested | |
79 | it, among some other tasks. In most cases there should be one per | |
80 | program. As, given a video URL, the downloader doesn't know how to | |
81 | extract all the needed information, task that InfoExtractors do, it | |
82 | has to pass the URL to one of them. | |
83 | ||
84 | For this, YoutubeDL objects have a method that allows | |
85 | InfoExtractors to be registered in a given order. When it is passed | |
86 | a URL, the YoutubeDL object handles it to the first InfoExtractor it | |
87 | finds that reports being able to handle it. The InfoExtractor extracts | |
88 | all the information about the video or videos the URL refers to, and | |
89 | YoutubeDL process the extracted information, possibly using a File | |
90 | Downloader to download the video. | |
91 | ||
92 | YoutubeDL objects accept a lot of parameters. In order not to saturate | |
93 | the object constructor with arguments, it receives a dictionary of | |
94 | options instead. These options are available through the params | |
95 | attribute for the InfoExtractors to use. The YoutubeDL also | |
96 | registers itself as the downloader in charge for the InfoExtractors | |
97 | that are added to it, so this is a "mutual registration". | |
98 | ||
99 | Available options: | |
100 | ||
101 | username: Username for authentication purposes. | |
102 | password: Password for authentication purposes. | |
c6c19746 | 103 | videopassword: Password for acces a video. |
8222d8de JMF |
104 | usenetrc: Use netrc for authentication instead. |
105 | verbose: Print additional info to stdout. | |
106 | quiet: Do not print messages to stdout. | |
ad8915b7 | 107 | no_warnings: Do not print out anything for warnings. |
8222d8de JMF |
108 | forceurl: Force printing final URL. |
109 | forcetitle: Force printing title. | |
110 | forceid: Force printing ID. | |
111 | forcethumbnail: Force printing thumbnail URL. | |
112 | forcedescription: Force printing description. | |
113 | forcefilename: Force printing final filename. | |
525ef922 | 114 | forceduration: Force printing duration. |
8694c600 | 115 | forcejson: Force printing info_dict as JSON. |
63e0be34 PH |
116 | dump_single_json: Force printing the info_dict of the whole playlist |
117 | (or video) as a single JSON line. | |
8222d8de JMF |
118 | simulate: Do not download the video files. |
119 | format: Video format code. | |
120 | format_limit: Highest quality format to try. | |
121 | outtmpl: Template for output names. | |
122 | restrictfilenames: Do not allow "&" and spaces in file names | |
123 | ignoreerrors: Do not stop on download errors. | |
124 | nooverwrites: Prevent overwriting files. | |
125 | playliststart: Playlist item to start at. | |
126 | playlistend: Playlist item to end at. | |
127 | matchtitle: Download only matching titles. | |
128 | rejecttitle: Reject downloads for matching titles. | |
8bf9319e | 129 | logger: Log messages to a logging.Logger instance. |
8222d8de JMF |
130 | logtostderr: Log messages to stderr instead of stdout. |
131 | writedescription: Write the video description to a .description file | |
132 | writeinfojson: Write the video description to a .info.json file | |
1fb07d10 | 133 | writeannotations: Write the video annotations to a .annotations.xml file |
8222d8de JMF |
134 | writethumbnail: Write the thumbnail image to a file |
135 | writesubtitles: Write the video subtitles to a file | |
b004821f | 136 | writeautomaticsub: Write the automatic subtitles to a file |
8222d8de | 137 | allsubtitles: Downloads all the subtitles of the video |
0b7f3118 | 138 | (requires writesubtitles or writeautomaticsub) |
8222d8de | 139 | listsubtitles: Lists all available subtitles for the video |
b98a6b2f | 140 | subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt) |
aa6a10c4 | 141 | subtitleslangs: List of languages of the subtitles to download |
8222d8de JMF |
142 | keepvideo: Keep the video file after post-processing |
143 | daterange: A DateRange object, download only if the upload_date is in the range. | |
144 | skip_download: Skip the actual download of the video file | |
c35f9e72 | 145 | cachedir: Location of the cache files in the filesystem. |
a0e07d31 | 146 | False to disable filesystem cache. |
47192f92 | 147 | noplaylist: Download single video instead of a playlist if in doubt. |
8dbe9899 PH |
148 | age_limit: An integer representing the user's age in years. |
149 | Unsuitable videos for the given age are skipped. | |
5fe18bdb PH |
150 | min_views: An integer representing the minimum view count the video |
151 | must have in order to not be skipped. | |
152 | Videos without view count information are always | |
153 | downloaded. None for no limit. | |
154 | max_views: An integer representing the maximum view count. | |
155 | Videos that are more popular than that are not | |
156 | downloaded. | |
157 | Videos without view count information are always | |
158 | downloaded. None for no limit. | |
159 | download_archive: File name of a file where all downloads are recorded. | |
c1c9a79c PH |
160 | Videos already present in the file are not downloaded |
161 | again. | |
dca08720 | 162 | cookiefile: File name where cookies should be read from and dumped to. |
a1ee09e8 | 163 | nocheckcertificate:Do not verify SSL certificates |
7e8c0af0 PH |
164 | prefer_insecure: Use HTTP instead of HTTPS to retrieve information. |
165 | At the moment, this is only supported by YouTube. | |
a1ee09e8 | 166 | proxy: URL of the proxy server to use |
e344693b | 167 | socket_timeout: Time to wait for unresponsive hosts, in seconds |
0783b09b PH |
168 | bidi_workaround: Work around buggy terminals without bidirectional text |
169 | support, using fridibi | |
a0ddb8a2 | 170 | debug_printtraffic:Print out sent and received HTTP traffic |
7b0817e8 | 171 | include_ads: Download ads as well |
04b4d394 PH |
172 | default_search: Prepend this string if an input url is not valid. |
173 | 'auto' for elaborate guessing | |
62fec3b2 | 174 | encoding: Use this encoding instead of the system-specified. |
e8ee972c | 175 | extract_flat: Do not resolve URLs, return the immediate result. |
057a5206 PH |
176 | Pass in 'in_playlist' to only show this behavior for |
177 | playlist items. | |
fe7e0c98 | 178 | |
8222d8de JMF |
179 | The following parameters are not used by YoutubeDL itself, they are used by |
180 | the FileDownloader: | |
181 | nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, | |
182 | noresizebuffer, retries, continuedl, noprogress, consoletitle | |
76b1bd67 JMF |
183 | |
184 | The following options are used by the post processors: | |
185 | prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, | |
186 | otherwise prefer avconv. | |
8d31fa3c | 187 | exec_cmd: Arbitrary command to run after downloading |
8222d8de JMF |
188 | """ |
189 | ||
190 | params = None | |
191 | _ies = [] | |
192 | _pps = [] | |
193 | _download_retcode = None | |
194 | _num_downloads = None | |
195 | _screen_file = None | |
196 | ||
3511266b | 197 | def __init__(self, params=None, auto_init=True): |
8222d8de | 198 | """Create a FileDownloader object with the given options.""" |
e9f9a10f JMF |
199 | if params is None: |
200 | params = {} | |
8222d8de | 201 | self._ies = [] |
56c73665 | 202 | self._ies_instances = {} |
8222d8de | 203 | self._pps = [] |
933605d7 | 204 | self._progress_hooks = [] |
8222d8de JMF |
205 | self._download_retcode = 0 |
206 | self._num_downloads = 0 | |
207 | self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] | |
0783b09b | 208 | self._err_file = sys.stderr |
e9f9a10f | 209 | self.params = params |
a0e07d31 | 210 | self.cache = Cache(self) |
34308b30 | 211 | |
0783b09b | 212 | if params.get('bidi_workaround', False): |
1c088fa8 PH |
213 | try: |
214 | import pty | |
215 | master, slave = pty.openpty() | |
216 | width = get_term_width() | |
217 | if width is None: | |
218 | width_args = [] | |
219 | else: | |
220 | width_args = ['-w', str(width)] | |
5d681e96 | 221 | sp_kwargs = dict( |
1c088fa8 PH |
222 | stdin=subprocess.PIPE, |
223 | stdout=slave, | |
224 | stderr=self._err_file) | |
5d681e96 PH |
225 | try: |
226 | self._output_process = subprocess.Popen( | |
227 | ['bidiv'] + width_args, **sp_kwargs | |
228 | ) | |
229 | except OSError: | |
5d681e96 PH |
230 | self._output_process = subprocess.Popen( |
231 | ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) | |
232 | self._output_channel = os.fdopen(master, 'rb') | |
1c088fa8 PH |
233 | except OSError as ose: |
234 | if ose.errno == 2: | |
6febd1c1 | 235 | 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 $PATH.') |
1c088fa8 PH |
236 | else: |
237 | raise | |
0783b09b | 238 | |
34308b30 PH |
239 | if (sys.version_info >= (3,) and sys.platform != 'win32' and |
240 | sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] | |
53d9009b | 241 | and not params.get('restrictfilenames', False)): |
34308b30 PH |
242 | # On Python 3, the Unicode filesystem API will throw errors (#1474) |
243 | self.report_warning( | |
6febd1c1 | 244 | 'Assuming --restrict-filenames since file system encoding ' |
1b725173 | 245 | 'cannot encode all characters. ' |
6febd1c1 | 246 | 'Set the LC_ALL environment variable to fix this.') |
4a98cdbf | 247 | self.params['restrictfilenames'] = True |
34308b30 | 248 | |
a3927cf7 | 249 | if '%(stitle)s' in self.params.get('outtmpl', ''): |
6febd1c1 | 250 | self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') |
8222d8de | 251 | |
dca08720 PH |
252 | self._setup_opener() |
253 | ||
3511266b PH |
254 | if auto_init: |
255 | self.print_debug_header() | |
256 | self.add_default_info_extractors() | |
257 | ||
7d4111ed PH |
258 | def warn_if_short_id(self, argv): |
259 | # short YouTube ID starting with dash? | |
260 | idxs = [ | |
261 | i for i, a in enumerate(argv) | |
262 | if re.match(r'^-[0-9A-Za-z_-]{10}$', a)] | |
263 | if idxs: | |
264 | correct_argv = ( | |
265 | ['youtube-dl'] + | |
266 | [a for i, a in enumerate(argv) if i not in idxs] + | |
267 | ['--'] + [argv[i] for i in idxs] | |
268 | ) | |
269 | self.report_warning( | |
270 | 'Long argument string detected. ' | |
271 | 'Use -- to separate parameters and URLs, like this:\n%s\n' % | |
272 | args_to_str(correct_argv)) | |
273 | ||
8222d8de JMF |
274 | def add_info_extractor(self, ie): |
275 | """Add an InfoExtractor object to the end of the list.""" | |
276 | self._ies.append(ie) | |
56c73665 | 277 | self._ies_instances[ie.ie_key()] = ie |
8222d8de JMF |
278 | ie.set_downloader(self) |
279 | ||
56c73665 JMF |
280 | def get_info_extractor(self, ie_key): |
281 | """ | |
282 | Get an instance of an IE with name ie_key, it will try to get one from | |
283 | the _ies list, if there's no instance it will create a new one and add | |
284 | it to the extractor list. | |
285 | """ | |
286 | ie = self._ies_instances.get(ie_key) | |
287 | if ie is None: | |
288 | ie = get_info_extractor(ie_key)() | |
289 | self.add_info_extractor(ie) | |
290 | return ie | |
291 | ||
023fa8c4 JMF |
292 | def add_default_info_extractors(self): |
293 | """ | |
294 | Add the InfoExtractors returned by gen_extractors to the end of the list | |
295 | """ | |
296 | for ie in gen_extractors(): | |
297 | self.add_info_extractor(ie) | |
298 | ||
8222d8de JMF |
299 | def add_post_processor(self, pp): |
300 | """Add a PostProcessor object to the end of the chain.""" | |
301 | self._pps.append(pp) | |
302 | pp.set_downloader(self) | |
303 | ||
933605d7 JMF |
304 | def add_progress_hook(self, ph): |
305 | """Add the progress hook (currently only for the file downloader)""" | |
306 | self._progress_hooks.append(ph) | |
8ab470f1 | 307 | |
1c088fa8 | 308 | def _bidi_workaround(self, message): |
5d681e96 | 309 | if not hasattr(self, '_output_channel'): |
1c088fa8 PH |
310 | return message |
311 | ||
5d681e96 | 312 | assert hasattr(self, '_output_process') |
11b85ce6 | 313 | assert isinstance(message, compat_str) |
6febd1c1 PH |
314 | line_count = message.count('\n') + 1 |
315 | self._output_process.stdin.write((message + '\n').encode('utf-8')) | |
5d681e96 | 316 | self._output_process.stdin.flush() |
6febd1c1 | 317 | res = ''.join(self._output_channel.readline().decode('utf-8') |
1c088fa8 | 318 | for _ in range(line_count)) |
6febd1c1 | 319 | return res[:-len('\n')] |
1c088fa8 | 320 | |
8222d8de | 321 | def to_screen(self, message, skip_eol=False): |
0783b09b PH |
322 | """Print message to stdout if not in quiet mode.""" |
323 | return self.to_stdout(message, skip_eol, check_quiet=True) | |
324 | ||
734f90bb | 325 | def _write_string(self, s, out=None): |
b58ddb32 | 326 | write_string(s, out=out, encoding=self.params.get('encoding')) |
734f90bb | 327 | |
0783b09b | 328 | def to_stdout(self, message, skip_eol=False, check_quiet=False): |
8222d8de | 329 | """Print message to stdout if not in quiet mode.""" |
8bf9319e | 330 | if self.params.get('logger'): |
43afe285 | 331 | self.params['logger'].debug(message) |
0783b09b | 332 | elif not check_quiet or not self.params.get('quiet', False): |
1c088fa8 | 333 | message = self._bidi_workaround(message) |
6febd1c1 | 334 | terminator = ['\n', ''][skip_eol] |
8222d8de | 335 | output = message + terminator |
1c088fa8 | 336 | |
734f90bb | 337 | self._write_string(output, self._screen_file) |
8222d8de JMF |
338 | |
339 | def to_stderr(self, message): | |
340 | """Print message to stderr.""" | |
11b85ce6 | 341 | assert isinstance(message, compat_str) |
8bf9319e | 342 | if self.params.get('logger'): |
43afe285 IB |
343 | self.params['logger'].error(message) |
344 | else: | |
1c088fa8 | 345 | message = self._bidi_workaround(message) |
6febd1c1 | 346 | output = message + '\n' |
734f90bb | 347 | self._write_string(output, self._err_file) |
8222d8de | 348 | |
1e5b9a95 PH |
349 | def to_console_title(self, message): |
350 | if not self.params.get('consoletitle', False): | |
351 | return | |
352 | if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): | |
353 | # c_wchar_p() might not be necessary if `message` is | |
354 | # already of type unicode() | |
355 | ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) | |
356 | elif 'TERM' in os.environ: | |
734f90bb | 357 | self._write_string('\033]0;%s\007' % message, self._screen_file) |
1e5b9a95 | 358 | |
bdde425c PH |
359 | def save_console_title(self): |
360 | if not self.params.get('consoletitle', False): | |
361 | return | |
362 | if 'TERM' in os.environ: | |
efd6c574 | 363 | # Save the title on stack |
734f90bb | 364 | self._write_string('\033[22;0t', self._screen_file) |
bdde425c PH |
365 | |
366 | def restore_console_title(self): | |
367 | if not self.params.get('consoletitle', False): | |
368 | return | |
369 | if 'TERM' in os.environ: | |
efd6c574 | 370 | # Restore the title from stack |
734f90bb | 371 | self._write_string('\033[23;0t', self._screen_file) |
bdde425c PH |
372 | |
373 | def __enter__(self): | |
374 | self.save_console_title() | |
375 | return self | |
376 | ||
377 | def __exit__(self, *args): | |
378 | self.restore_console_title() | |
f89197d7 | 379 | |
dca08720 PH |
380 | if self.params.get('cookiefile') is not None: |
381 | self.cookiejar.save() | |
bdde425c | 382 | |
8222d8de JMF |
383 | def trouble(self, message=None, tb=None): |
384 | """Determine action to take when a download problem appears. | |
385 | ||
386 | Depending on if the downloader has been configured to ignore | |
387 | download errors or not, this method may throw an exception or | |
388 | not when errors are found, after printing the message. | |
389 | ||
390 | tb, if given, is additional traceback information. | |
391 | """ | |
392 | if message is not None: | |
393 | self.to_stderr(message) | |
394 | if self.params.get('verbose'): | |
395 | if tb is None: | |
396 | if sys.exc_info()[0]: # if .trouble has been called from an except block | |
6febd1c1 | 397 | tb = '' |
8222d8de | 398 | if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: |
6febd1c1 | 399 | tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) |
8222d8de JMF |
400 | tb += compat_str(traceback.format_exc()) |
401 | else: | |
402 | tb_data = traceback.format_list(traceback.extract_stack()) | |
6febd1c1 | 403 | tb = ''.join(tb_data) |
8222d8de JMF |
404 | self.to_stderr(tb) |
405 | if not self.params.get('ignoreerrors', False): | |
406 | if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: | |
407 | exc_info = sys.exc_info()[1].exc_info | |
408 | else: | |
409 | exc_info = sys.exc_info() | |
410 | raise DownloadError(message, exc_info) | |
411 | self._download_retcode = 1 | |
412 | ||
413 | def report_warning(self, message): | |
414 | ''' | |
415 | Print the message to stderr, it will be prefixed with 'WARNING:' | |
416 | If stderr is a tty file the 'WARNING:' will be colored | |
417 | ''' | |
6d07ce01 JMF |
418 | if self.params.get('logger') is not None: |
419 | self.params['logger'].warning(message) | |
8222d8de | 420 | else: |
ad8915b7 PH |
421 | if self.params.get('no_warnings'): |
422 | return | |
6d07ce01 JMF |
423 | if self._err_file.isatty() and os.name != 'nt': |
424 | _msg_header = '\033[0;33mWARNING:\033[0m' | |
425 | else: | |
426 | _msg_header = 'WARNING:' | |
427 | warning_message = '%s %s' % (_msg_header, message) | |
428 | self.to_stderr(warning_message) | |
8222d8de JMF |
429 | |
430 | def report_error(self, message, tb=None): | |
431 | ''' | |
432 | Do the same as trouble, but prefixes the message with 'ERROR:', colored | |
433 | in red if stderr is a tty file. | |
434 | ''' | |
0783b09b | 435 | if self._err_file.isatty() and os.name != 'nt': |
6febd1c1 | 436 | _msg_header = '\033[0;31mERROR:\033[0m' |
8222d8de | 437 | else: |
6febd1c1 PH |
438 | _msg_header = 'ERROR:' |
439 | error_message = '%s %s' % (_msg_header, message) | |
8222d8de JMF |
440 | self.trouble(error_message, tb) |
441 | ||
8222d8de JMF |
442 | def report_file_already_downloaded(self, file_name): |
443 | """Report file has already been fully downloaded.""" | |
444 | try: | |
6febd1c1 | 445 | self.to_screen('[download] %s has already been downloaded' % file_name) |
ce02ed60 | 446 | except UnicodeEncodeError: |
6febd1c1 | 447 | self.to_screen('[download] The file has already been downloaded') |
8222d8de | 448 | |
8222d8de JMF |
449 | def prepare_filename(self, info_dict): |
450 | """Generate the output filename.""" | |
451 | try: | |
452 | template_dict = dict(info_dict) | |
453 | ||
454 | template_dict['epoch'] = int(time.time()) | |
455 | autonumber_size = self.params.get('autonumber_size') | |
456 | if autonumber_size is None: | |
457 | autonumber_size = 5 | |
6febd1c1 | 458 | autonumber_templ = '%0' + str(autonumber_size) + 'd' |
8222d8de | 459 | template_dict['autonumber'] = autonumber_templ % self._num_downloads |
702665c0 | 460 | if template_dict.get('playlist_index') is not None: |
c6b4132a | 461 | template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index']) |
17b75c0d PH |
462 | if template_dict.get('resolution') is None: |
463 | if template_dict.get('width') and template_dict.get('height'): | |
464 | template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height']) | |
465 | elif template_dict.get('height'): | |
805ef3c6 | 466 | template_dict['resolution'] = '%sp' % template_dict['height'] |
17b75c0d | 467 | elif template_dict.get('width'): |
805ef3c6 | 468 | template_dict['resolution'] = '?x%d' % template_dict['width'] |
8222d8de | 469 | |
586a91b6 | 470 | sanitize = lambda k, v: sanitize_filename( |
45598aab | 471 | compat_str(v), |
8222d8de | 472 | restricted=self.params.get('restrictfilenames'), |
6febd1c1 | 473 | is_id=(k == 'id')) |
586a91b6 | 474 | template_dict = dict((k, sanitize(k, v)) |
45598aab PH |
475 | for k, v in template_dict.items() |
476 | if v is not None) | |
6febd1c1 | 477 | template_dict = collections.defaultdict(lambda: 'NA', template_dict) |
8222d8de | 478 | |
acd69589 | 479 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
4644ac55 | 480 | tmpl = compat_expanduser(outtmpl) |
586a91b6 | 481 | filename = tmpl % template_dict |
8222d8de | 482 | return filename |
8222d8de | 483 | except ValueError as err: |
6febd1c1 | 484 | self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') |
8222d8de JMF |
485 | return None |
486 | ||
487 | def _match_entry(self, info_dict): | |
488 | """ Returns None iff the file should be downloaded """ | |
489 | ||
6febd1c1 | 490 | video_title = info_dict.get('title', info_dict.get('id', 'video')) |
7012b23c PH |
491 | if 'title' in info_dict: |
492 | # This can happen when we're just evaluating the playlist | |
493 | title = info_dict['title'] | |
494 | matchtitle = self.params.get('matchtitle', False) | |
495 | if matchtitle: | |
496 | if not re.search(matchtitle, title, re.IGNORECASE): | |
6febd1c1 | 497 | return '"' + title + '" title did not match pattern "' + matchtitle + '"' |
7012b23c PH |
498 | rejecttitle = self.params.get('rejecttitle', False) |
499 | if rejecttitle: | |
500 | if re.search(rejecttitle, title, re.IGNORECASE): | |
6febd1c1 | 501 | return '"' + title + '" title matched reject pattern "' + rejecttitle + '"' |
8222d8de JMF |
502 | date = info_dict.get('upload_date', None) |
503 | if date is not None: | |
504 | dateRange = self.params.get('daterange', DateRange()) | |
505 | if date not in dateRange: | |
6febd1c1 | 506 | return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) |
5fe18bdb PH |
507 | view_count = info_dict.get('view_count', None) |
508 | if view_count is not None: | |
509 | min_views = self.params.get('min_views') | |
510 | if min_views is not None and view_count < min_views: | |
6febd1c1 | 511 | return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views) |
5fe18bdb PH |
512 | max_views = self.params.get('max_views') |
513 | if max_views is not None and view_count > max_views: | |
6febd1c1 | 514 | return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views) |
8dbe9899 PH |
515 | age_limit = self.params.get('age_limit') |
516 | if age_limit is not None: | |
be843678 PH |
517 | actual_age_limit = info_dict.get('age_limit') |
518 | if actual_age_limit is None: | |
519 | actual_age_limit = 0 | |
520 | if age_limit < actual_age_limit: | |
6febd1c1 | 521 | return 'Skipping "' + title + '" because it is age restricted' |
c1c9a79c | 522 | if self.in_download_archive(info_dict): |
6febd1c1 | 523 | return '%s has already been recorded in archive' % video_title |
8222d8de | 524 | return None |
fe7e0c98 | 525 | |
b6c45014 JMF |
526 | @staticmethod |
527 | def add_extra_info(info_dict, extra_info): | |
528 | '''Set the keys from extra_info in info dict if they are missing''' | |
529 | for key, value in extra_info.items(): | |
530 | info_dict.setdefault(key, value) | |
531 | ||
7fc3fa05 PH |
532 | def extract_info(self, url, download=True, ie_key=None, extra_info={}, |
533 | process=True): | |
8222d8de JMF |
534 | ''' |
535 | Returns a list with a dictionary for each video we find. | |
536 | If 'download', also downloads the videos. | |
537 | extra_info is a dict containing the extra values to add to each result | |
538 | ''' | |
fe7e0c98 | 539 | |
8222d8de | 540 | if ie_key: |
56c73665 | 541 | ies = [self.get_info_extractor(ie_key)] |
8222d8de JMF |
542 | else: |
543 | ies = self._ies | |
544 | ||
545 | for ie in ies: | |
546 | if not ie.suitable(url): | |
547 | continue | |
548 | ||
549 | if not ie.working(): | |
6febd1c1 PH |
550 | self.report_warning('The program functionality for this site has been marked as broken, ' |
551 | 'and will probably not work.') | |
8222d8de JMF |
552 | |
553 | try: | |
554 | ie_result = ie.extract(url) | |
555 | if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) | |
556 | break | |
557 | if isinstance(ie_result, list): | |
558 | # Backwards compatibility: old IE result format | |
8222d8de JMF |
559 | ie_result = { |
560 | '_type': 'compat_list', | |
561 | 'entries': ie_result, | |
562 | } | |
ea38e55f | 563 | self.add_default_extra_info(ie_result, ie, url) |
7fc3fa05 PH |
564 | if process: |
565 | return self.process_ie_result(ie_result, download, extra_info) | |
566 | else: | |
567 | return ie_result | |
8222d8de JMF |
568 | except ExtractorError as de: # An error we somewhat expected |
569 | self.report_error(compat_str(de), de.format_traceback()) | |
570 | break | |
d3e5bbf4 PH |
571 | except MaxDownloadsReached: |
572 | raise | |
8222d8de JMF |
573 | except Exception as e: |
574 | if self.params.get('ignoreerrors', False): | |
575 | self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) | |
576 | break | |
577 | else: | |
578 | raise | |
579 | else: | |
1a489545 | 580 | self.report_error('no suitable InfoExtractor for URL %s' % url) |
fe7e0c98 | 581 | |
ea38e55f PH |
582 | def add_default_extra_info(self, ie_result, ie, url): |
583 | self.add_extra_info(ie_result, { | |
584 | 'extractor': ie.IE_NAME, | |
585 | 'webpage_url': url, | |
586 | 'webpage_url_basename': url_basename(url), | |
587 | 'extractor_key': ie.ie_key(), | |
588 | }) | |
589 | ||
8222d8de JMF |
590 | def process_ie_result(self, ie_result, download=True, extra_info={}): |
591 | """ | |
592 | Take the result of the ie(may be modified) and resolve all unresolved | |
593 | references (URLs, playlist items). | |
594 | ||
595 | It will also download the videos if 'download'. | |
596 | Returns the resolved ie_result. | |
597 | """ | |
598 | ||
e8ee972c PH |
599 | result_type = ie_result.get('_type', 'video') |
600 | ||
057a5206 PH |
601 | if result_type in ('url', 'url_transparent'): |
602 | extract_flat = self.params.get('extract_flat', False) | |
603 | if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or | |
604 | extract_flat is True): | |
057a5206 PH |
605 | if self.params.get('forcejson', False): |
606 | self.to_stdout(json.dumps(ie_result)) | |
e8ee972c PH |
607 | return ie_result |
608 | ||
8222d8de | 609 | if result_type == 'video': |
b6c45014 | 610 | self.add_extra_info(ie_result, extra_info) |
feee2ecf | 611 | return self.process_video_result(ie_result, download=download) |
8222d8de JMF |
612 | elif result_type == 'url': |
613 | # We have to add extra_info to the results because it may be | |
614 | # contained in a playlist | |
615 | return self.extract_info(ie_result['url'], | |
616 | download, | |
617 | ie_key=ie_result.get('ie_key'), | |
618 | extra_info=extra_info) | |
7fc3fa05 PH |
619 | elif result_type == 'url_transparent': |
620 | # Use the information from the embedding page | |
621 | info = self.extract_info( | |
622 | ie_result['url'], ie_key=ie_result.get('ie_key'), | |
623 | extra_info=extra_info, download=False, process=False) | |
624 | ||
625 | def make_result(embedded_info): | |
626 | new_result = ie_result.copy() | |
627 | for f in ('_type', 'url', 'ext', 'player_url', 'formats', | |
1538eff6 | 628 | 'entries', 'ie_key', 'duration', |
ef4fd848 PH |
629 | 'subtitles', 'annotations', 'format', |
630 | 'thumbnail', 'thumbnails'): | |
7fc3fa05 PH |
631 | if f in new_result: |
632 | del new_result[f] | |
633 | if f in embedded_info: | |
634 | new_result[f] = embedded_info[f] | |
635 | return new_result | |
636 | new_result = make_result(info) | |
637 | ||
638 | assert new_result.get('_type') != 'url_transparent' | |
639 | if new_result.get('_type') == 'compat_list': | |
640 | new_result['entries'] = [ | |
641 | make_result(e) for e in new_result['entries']] | |
642 | ||
643 | return self.process_ie_result( | |
644 | new_result, download=download, extra_info=extra_info) | |
42e12102 | 645 | elif result_type == 'playlist' or result_type == 'multi_video': |
8222d8de JMF |
646 | # We process each entry in the playlist |
647 | playlist = ie_result.get('title', None) or ie_result.get('id', None) | |
6febd1c1 | 648 | self.to_screen('[download] Downloading playlist: %s' % playlist) |
8222d8de JMF |
649 | |
650 | playlist_results = [] | |
651 | ||
8222d8de | 652 | playliststart = self.params.get('playliststart', 1) - 1 |
a19fd00c PH |
653 | playlistend = self.params.get('playlistend', None) |
654 | # For backwards compatibility, interpret -1 as whole list | |
8222d8de | 655 | if playlistend == -1: |
a19fd00c | 656 | playlistend = None |
8222d8de | 657 | |
b7ab0590 PH |
658 | if isinstance(ie_result['entries'], list): |
659 | n_all_entries = len(ie_result['entries']) | |
660 | entries = ie_result['entries'][playliststart:playlistend] | |
661 | n_entries = len(entries) | |
662 | self.to_screen( | |
663 | "[%s] playlist %s: Collected %d video ids (downloading %d of them)" % | |
664 | (ie_result['extractor'], playlist, n_all_entries, n_entries)) | |
665 | else: | |
666 | assert isinstance(ie_result['entries'], PagedList) | |
667 | entries = ie_result['entries'].getslice( | |
668 | playliststart, playlistend) | |
669 | n_entries = len(entries) | |
670 | self.to_screen( | |
671 | "[%s] playlist %s: Downloading %d videos" % | |
672 | (ie_result['extractor'], playlist, n_entries)) | |
8222d8de | 673 | |
fe7e0c98 | 674 | for i, entry in enumerate(entries, 1): |
6febd1c1 | 675 | self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries)) |
8222d8de | 676 | extra = { |
c6b4132a | 677 | 'n_entries': n_entries, |
fe7e0c98 | 678 | 'playlist': playlist, |
a1cf99d0 PH |
679 | 'playlist_id': ie_result.get('id'), |
680 | 'playlist_title': ie_result.get('title'), | |
fe7e0c98 | 681 | 'playlist_index': i + playliststart, |
b6c45014 | 682 | 'extractor': ie_result['extractor'], |
9103bbc5 | 683 | 'webpage_url': ie_result['webpage_url'], |
29eb5174 | 684 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 685 | 'extractor_key': ie_result['extractor_key'], |
fe7e0c98 | 686 | } |
7012b23c PH |
687 | |
688 | reason = self._match_entry(entry) | |
689 | if reason is not None: | |
6febd1c1 | 690 | self.to_screen('[download] ' + reason) |
7012b23c PH |
691 | continue |
692 | ||
8222d8de JMF |
693 | entry_result = self.process_ie_result(entry, |
694 | download=download, | |
695 | extra_info=extra) | |
696 | playlist_results.append(entry_result) | |
697 | ie_result['entries'] = playlist_results | |
698 | return ie_result | |
699 | elif result_type == 'compat_list': | |
c9bf4114 PH |
700 | self.report_warning( |
701 | 'Extractor %s returned a compat_list result. ' | |
702 | 'It needs to be updated.' % ie_result.get('extractor')) | |
8222d8de | 703 | def _fixup(r): |
b6c45014 | 704 | self.add_extra_info(r, |
9103bbc5 JMF |
705 | { |
706 | 'extractor': ie_result['extractor'], | |
707 | 'webpage_url': ie_result['webpage_url'], | |
29eb5174 | 708 | 'webpage_url_basename': url_basename(ie_result['webpage_url']), |
be97abc2 | 709 | 'extractor_key': ie_result['extractor_key'], |
9103bbc5 | 710 | }) |
8222d8de JMF |
711 | return r |
712 | ie_result['entries'] = [ | |
b6c45014 | 713 | self.process_ie_result(_fixup(r), download, extra_info) |
8222d8de JMF |
714 | for r in ie_result['entries'] |
715 | ] | |
716 | return ie_result | |
717 | else: | |
718 | raise Exception('Invalid result type: %s' % result_type) | |
719 | ||
a9c58ad9 JMF |
720 | def select_format(self, format_spec, available_formats): |
721 | if format_spec == 'best' or format_spec is None: | |
722 | return available_formats[-1] | |
723 | elif format_spec == 'worst': | |
724 | return available_formats[0] | |
ba7678f9 PH |
725 | elif format_spec == 'bestaudio': |
726 | audio_formats = [ | |
727 | f for f in available_formats | |
728 | if f.get('vcodec') == 'none'] | |
729 | if audio_formats: | |
730 | return audio_formats[-1] | |
731 | elif format_spec == 'worstaudio': | |
732 | audio_formats = [ | |
733 | f for f in available_formats | |
734 | if f.get('vcodec') == 'none'] | |
735 | if audio_formats: | |
736 | return audio_formats[0] | |
bc6d5978 JMF |
737 | elif format_spec == 'bestvideo': |
738 | video_formats = [ | |
739 | f for f in available_formats | |
740 | if f.get('acodec') == 'none'] | |
741 | if video_formats: | |
742 | return video_formats[-1] | |
743 | elif format_spec == 'worstvideo': | |
744 | video_formats = [ | |
745 | f for f in available_formats | |
746 | if f.get('acodec') == 'none'] | |
747 | if video_formats: | |
748 | return video_formats[0] | |
a9c58ad9 | 749 | else: |
e2e5dae6 | 750 | extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a'] |
49e86983 JMF |
751 | if format_spec in extensions: |
752 | filter_f = lambda f: f['ext'] == format_spec | |
753 | else: | |
754 | filter_f = lambda f: f['format_id'] == format_spec | |
fe7e0c98 | 755 | matches = list(filter(filter_f, available_formats)) |
a9c58ad9 JMF |
756 | if matches: |
757 | return matches[-1] | |
758 | return None | |
759 | ||
dd82ffea JMF |
760 | def process_video_result(self, info_dict, download=True): |
761 | assert info_dict.get('_type', 'video') == 'video' | |
762 | ||
bec1fad2 PH |
763 | if 'id' not in info_dict: |
764 | raise ExtractorError('Missing "id" field in extractor result') | |
765 | if 'title' not in info_dict: | |
766 | raise ExtractorError('Missing "title" field in extractor result') | |
767 | ||
dd82ffea JMF |
768 | if 'playlist' not in info_dict: |
769 | # It isn't part of a playlist | |
770 | info_dict['playlist'] = None | |
771 | info_dict['playlist_index'] = None | |
772 | ||
d5519808 PH |
773 | thumbnails = info_dict.get('thumbnails') |
774 | if thumbnails: | |
be6d7229 PH |
775 | thumbnails.sort(key=lambda t: ( |
776 | t.get('width'), t.get('height'), t.get('url'))) | |
d5519808 PH |
777 | for t in thumbnails: |
778 | if 'width' in t and 'height' in t: | |
779 | t['resolution'] = '%dx%d' % (t['width'], t['height']) | |
780 | ||
781 | if thumbnails and 'thumbnail' not in info_dict: | |
782 | info_dict['thumbnail'] = thumbnails[-1]['url'] | |
783 | ||
c9ae7b95 | 784 | if 'display_id' not in info_dict and 'id' in info_dict: |
0afef30b PH |
785 | info_dict['display_id'] = info_dict['id'] |
786 | ||
955c4514 | 787 | if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None: |
9d2ecdbc | 788 | upload_date = datetime.datetime.utcfromtimestamp( |
955c4514 | 789 | info_dict['timestamp']) |
9d2ecdbc PH |
790 | info_dict['upload_date'] = upload_date.strftime('%Y%m%d') |
791 | ||
6ff000b8 | 792 | # This extractors handle format selection themselves |
6febd1c1 | 793 | if info_dict['extractor'] in ['Youku']: |
12893efe JMF |
794 | if download: |
795 | self.process_info(info_dict) | |
6ff000b8 JMF |
796 | return info_dict |
797 | ||
dd82ffea JMF |
798 | # We now pick which formats have to be downloaded |
799 | if info_dict.get('formats') is None: | |
800 | # There's only one format available | |
801 | formats = [info_dict] | |
802 | else: | |
803 | formats = info_dict['formats'] | |
804 | ||
db95dc13 PH |
805 | if not formats: |
806 | raise ExtractorError('No video formats found!') | |
807 | ||
dd82ffea | 808 | # We check that all the formats have the format and format_id fields |
db95dc13 | 809 | for i, format in enumerate(formats): |
bec1fad2 PH |
810 | if 'url' not in format: |
811 | raise ExtractorError('Missing "url" key in result (index %d)' % i) | |
812 | ||
dd82ffea | 813 | if format.get('format_id') is None: |
8016c922 | 814 | format['format_id'] = compat_str(i) |
8c51aa65 | 815 | if format.get('format') is None: |
6febd1c1 | 816 | format['format'] = '{id} - {res}{note}'.format( |
8c51aa65 JMF |
817 | id=format['format_id'], |
818 | res=self.format_resolution(format), | |
6febd1c1 | 819 | note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '', |
8c51aa65 | 820 | ) |
c1002e96 PH |
821 | # Automatically determine file extension if missing |
822 | if 'ext' not in format: | |
cce929ea | 823 | format['ext'] = determine_ext(format['url']).lower() |
dd82ffea | 824 | |
99e206d5 JMF |
825 | format_limit = self.params.get('format_limit', None) |
826 | if format_limit: | |
f4d96df0 PH |
827 | formats = list(takewhile_inclusive( |
828 | lambda f: f['format_id'] != format_limit, formats | |
829 | )) | |
4bcc7bd1 PH |
830 | |
831 | # TODO Central sorting goes here | |
99e206d5 | 832 | |
f89197d7 | 833 | if formats[0] is not info_dict: |
b3d9ef88 JMF |
834 | # only set the 'formats' fields if the original info_dict list them |
835 | # otherwise we end up with a circular reference, the first (and unique) | |
f89197d7 | 836 | # element in the 'formats' field in info_dict is info_dict itself, |
b3d9ef88 JMF |
837 | # wich can't be exported to json |
838 | info_dict['formats'] = formats | |
bfaae0a7 | 839 | if self.params.get('listformats', None): |
840 | self.list_formats(info_dict) | |
841 | return | |
842 | ||
de3ef3ed | 843 | req_format = self.params.get('format') |
a9c58ad9 JMF |
844 | if req_format is None: |
845 | req_format = 'best' | |
dd82ffea | 846 | formats_to_download = [] |
dd82ffea | 847 | # The -1 is for supporting YoutubeIE |
a9c58ad9 | 848 | if req_format in ('-1', 'all'): |
dd82ffea JMF |
849 | formats_to_download = formats |
850 | else: | |
1de33faf PH |
851 | for rfstr in req_format.split(','): |
852 | # We can accept formats requested in the format: 34/5/best, we pick | |
853 | # the first that is available, starting from left | |
854 | req_formats = rfstr.split('/') | |
855 | for rf in req_formats: | |
856 | if re.match(r'.+?\+.+?', rf) is not None: | |
857 | # Two formats have been requested like '137+139' | |
858 | format_1, format_2 = rf.split('+') | |
859 | formats_info = (self.select_format(format_1, formats), | |
860 | self.select_format(format_2, formats)) | |
861 | if all(formats_info): | |
c2954908 JMF |
862 | # The first format must contain the video and the |
863 | # second the audio | |
864 | if formats_info[0].get('vcodec') == 'none': | |
865 | self.report_error('The first format must ' | |
866 | 'contain the video, try using ' | |
867 | '"-f %s+%s"' % (format_2, format_1)) | |
868 | return | |
1de33faf PH |
869 | selected_format = { |
870 | 'requested_formats': formats_info, | |
871 | 'format': rf, | |
872 | 'ext': formats_info[0]['ext'], | |
873 | } | |
874 | else: | |
875 | selected_format = None | |
6350728b | 876 | else: |
1de33faf PH |
877 | selected_format = self.select_format(rf, formats) |
878 | if selected_format is not None: | |
879 | formats_to_download.append(selected_format) | |
880 | break | |
dd82ffea | 881 | if not formats_to_download: |
6febd1c1 | 882 | raise ExtractorError('requested format not available', |
78a3a9f8 | 883 | expected=True) |
dd82ffea JMF |
884 | |
885 | if download: | |
886 | if len(formats_to_download) > 1: | |
6febd1c1 | 887 | self.to_screen('[info] %s: downloading video in %s formats' % (info_dict['id'], len(formats_to_download))) |
dd82ffea JMF |
888 | for format in formats_to_download: |
889 | new_info = dict(info_dict) | |
890 | new_info.update(format) | |
891 | self.process_info(new_info) | |
892 | # We update the info dict with the best quality format (backwards compatibility) | |
893 | info_dict.update(formats_to_download[-1]) | |
894 | return info_dict | |
895 | ||
8222d8de JMF |
896 | def process_info(self, info_dict): |
897 | """Process a single resolved IE result.""" | |
898 | ||
899 | assert info_dict.get('_type', 'video') == 'video' | |
fd288278 PH |
900 | |
901 | max_downloads = self.params.get('max_downloads') | |
902 | if max_downloads is not None: | |
903 | if self._num_downloads >= int(max_downloads): | |
904 | raise MaxDownloadsReached() | |
8222d8de JMF |
905 | |
906 | info_dict['fulltitle'] = info_dict['title'] | |
907 | if len(info_dict['title']) > 200: | |
6febd1c1 | 908 | info_dict['title'] = info_dict['title'][:197] + '...' |
8222d8de JMF |
909 | |
910 | # Keep for backwards compatibility | |
911 | info_dict['stitle'] = info_dict['title'] | |
912 | ||
11b85ce6 | 913 | if 'format' not in info_dict: |
8222d8de JMF |
914 | info_dict['format'] = info_dict['ext'] |
915 | ||
916 | reason = self._match_entry(info_dict) | |
917 | if reason is not None: | |
6febd1c1 | 918 | self.to_screen('[download] ' + reason) |
8222d8de JMF |
919 | return |
920 | ||
fd288278 | 921 | self._num_downloads += 1 |
8222d8de JMF |
922 | |
923 | filename = self.prepare_filename(info_dict) | |
924 | ||
925 | # Forced printings | |
926 | if self.params.get('forcetitle', False): | |
0783b09b | 927 | self.to_stdout(info_dict['fulltitle']) |
8222d8de | 928 | if self.params.get('forceid', False): |
0783b09b | 929 | self.to_stdout(info_dict['id']) |
8222d8de | 930 | if self.params.get('forceurl', False): |
edde6c56 | 931 | # For RTMP URLs, also include the playpath |
6febd1c1 | 932 | self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) |
216d71d0 | 933 | if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: |
0783b09b | 934 | self.to_stdout(info_dict['thumbnail']) |
216d71d0 | 935 | if self.params.get('forcedescription', False) and info_dict.get('description') is not None: |
0783b09b | 936 | self.to_stdout(info_dict['description']) |
8222d8de | 937 | if self.params.get('forcefilename', False) and filename is not None: |
0783b09b | 938 | self.to_stdout(filename) |
525ef922 PH |
939 | if self.params.get('forceduration', False) and info_dict.get('duration') is not None: |
940 | self.to_stdout(formatSeconds(info_dict['duration'])) | |
8222d8de | 941 | if self.params.get('forceformat', False): |
0783b09b | 942 | self.to_stdout(info_dict['format']) |
9d153818 | 943 | if self.params.get('forcejson', False): |
a0d96c98 | 944 | info_dict['_filename'] = filename |
0783b09b | 945 | self.to_stdout(json.dumps(info_dict)) |
63e0be34 PH |
946 | if self.params.get('dump_single_json', False): |
947 | info_dict['_filename'] = filename | |
8222d8de JMF |
948 | |
949 | # Do nothing else if in simulate mode | |
950 | if self.params.get('simulate', False): | |
951 | return | |
952 | ||
953 | if filename is None: | |
954 | return | |
955 | ||
956 | try: | |
957 | dn = os.path.dirname(encodeFilename(filename)) | |
d26e981d | 958 | if dn and not os.path.exists(dn): |
8222d8de JMF |
959 | os.makedirs(dn) |
960 | except (OSError, IOError) as err: | |
6febd1c1 | 961 | self.report_error('unable to create directory ' + compat_str(err)) |
8222d8de JMF |
962 | return |
963 | ||
964 | if self.params.get('writedescription', False): | |
6febd1c1 | 965 | descfn = filename + '.description' |
7b6fefc9 | 966 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)): |
6febd1c1 | 967 | self.to_screen('[info] Video description is already present') |
7b6fefc9 PH |
968 | else: |
969 | try: | |
6febd1c1 | 970 | self.to_screen('[info] Writing video description to: ' + descfn) |
7b6fefc9 PH |
971 | with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: |
972 | descfile.write(info_dict['description']) | |
973 | except (KeyError, TypeError): | |
6febd1c1 | 974 | self.report_warning('There\'s no description to write.') |
7b6fefc9 | 975 | except (OSError, IOError): |
6febd1c1 | 976 | self.report_error('Cannot write description file ' + descfn) |
7b6fefc9 | 977 | return |
8222d8de | 978 | |
1fb07d10 | 979 | if self.params.get('writeannotations', False): |
6febd1c1 | 980 | annofn = filename + '.annotations.xml' |
7b6fefc9 | 981 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): |
6febd1c1 | 982 | self.to_screen('[info] Video annotations are already present') |
7b6fefc9 PH |
983 | else: |
984 | try: | |
6febd1c1 | 985 | self.to_screen('[info] Writing video annotations to: ' + annofn) |
7b6fefc9 PH |
986 | with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: |
987 | annofile.write(info_dict['annotations']) | |
988 | except (KeyError, TypeError): | |
6febd1c1 | 989 | self.report_warning('There are no annotations to write.') |
7b6fefc9 | 990 | except (OSError, IOError): |
6febd1c1 | 991 | self.report_error('Cannot write annotations file: ' + annofn) |
7b6fefc9 | 992 | return |
1fb07d10 | 993 | |
c4a91be7 | 994 | subtitles_are_requested = any([self.params.get('writesubtitles', False), |
0b7f3118 | 995 | self.params.get('writeautomaticsub')]) |
c4a91be7 | 996 | |
fe7e0c98 | 997 | if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']: |
8222d8de JMF |
998 | # subtitles download errors are already managed as troubles in relevant IE |
999 | # that way it will silently go on when used with unsupporting IE | |
8222d8de | 1000 | subtitles = info_dict['subtitles'] |
ca715127 | 1001 | sub_format = self.params.get('subtitlesformat', 'srt') |
5d51a883 JMF |
1002 | for sub_lang in subtitles.keys(): |
1003 | sub = subtitles[sub_lang] | |
6804038d JMF |
1004 | if sub is None: |
1005 | continue | |
8222d8de | 1006 | try: |
d4051a8e | 1007 | sub_filename = subtitles_filename(filename, sub_lang, sub_format) |
7b6fefc9 | 1008 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): |
6febd1c1 | 1009 | self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format)) |
7b6fefc9 | 1010 | else: |
6febd1c1 | 1011 | self.to_screen('[info] Writing video subtitles to: ' + sub_filename) |
7b6fefc9 PH |
1012 | with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: |
1013 | subfile.write(sub) | |
8222d8de | 1014 | except (OSError, IOError): |
e4db1951 | 1015 | self.report_error('Cannot write subtitles file ' + sub_filename) |
8222d8de JMF |
1016 | return |
1017 | ||
8222d8de | 1018 | if self.params.get('writeinfojson', False): |
6febd1c1 | 1019 | infofn = os.path.splitext(filename)[0] + '.info.json' |
7b6fefc9 | 1020 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)): |
6febd1c1 | 1021 | self.to_screen('[info] Video description metadata is already present') |
7b6fefc9 | 1022 | else: |
6febd1c1 | 1023 | self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn) |
7b6fefc9 | 1024 | try: |
92120217 | 1025 | write_json_file(info_dict, infofn) |
7b6fefc9 | 1026 | except (OSError, IOError): |
6febd1c1 | 1027 | self.report_error('Cannot write metadata to JSON file ' + infofn) |
7b6fefc9 | 1028 | return |
8222d8de JMF |
1029 | |
1030 | if self.params.get('writethumbnail', False): | |
d8269e1d | 1031 | if info_dict.get('thumbnail') is not None: |
6febd1c1 PH |
1032 | thumb_format = determine_ext(info_dict['thumbnail'], 'jpg') |
1033 | thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format | |
0a9ce268 | 1034 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)): |
6febd1c1 | 1035 | self.to_screen('[%s] %s: Thumbnail is already present' % |
7b6fefc9 PH |
1036 | (info_dict['extractor'], info_dict['id'])) |
1037 | else: | |
6febd1c1 | 1038 | self.to_screen('[%s] %s: Downloading thumbnail ...' % |
7b6fefc9 PH |
1039 | (info_dict['extractor'], info_dict['id'])) |
1040 | try: | |
e9c092f1 | 1041 | uf = self.urlopen(info_dict['thumbnail']) |
7b6fefc9 PH |
1042 | with open(thumb_filename, 'wb') as thumbf: |
1043 | shutil.copyfileobj(uf, thumbf) | |
6febd1c1 | 1044 | self.to_screen('[%s] %s: Writing thumbnail to: %s' % |
7b6fefc9 PH |
1045 | (info_dict['extractor'], info_dict['id'], thumb_filename)) |
1046 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: | |
6febd1c1 | 1047 | self.report_warning('Unable to download thumbnail "%s": %s' % |
7b6fefc9 | 1048 | (info_dict['thumbnail'], compat_str(err))) |
8222d8de JMF |
1049 | |
1050 | if not self.params.get('skip_download', False): | |
1051 | if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): | |
1052 | success = True | |
1053 | else: | |
1054 | try: | |
6350728b JMF |
1055 | def dl(name, info): |
1056 | fd = get_suitable_downloader(info)(self, self.params) | |
1057 | for ph in self._progress_hooks: | |
1058 | fd.add_progress_hook(ph) | |
8d5797b0 PH |
1059 | if self.params.get('verbose'): |
1060 | self.to_stdout('[debug] Invoking downloader on %r' % info.get('url')) | |
6350728b JMF |
1061 | return fd.download(name, info) |
1062 | if info_dict.get('requested_formats') is not None: | |
1063 | downloaded = [] | |
1064 | success = True | |
b7f81164 | 1065 | merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) |
48844745 | 1066 | if not merger._executable: |
58c3c7ae JMF |
1067 | postprocessors = [] |
1068 | self.report_warning('You have requested multiple ' | |
1069 | 'formats but ffmpeg or avconv are not installed.' | |
1070 | ' The formats won\'t be merged') | |
1071 | else: | |
1072 | postprocessors = [merger] | |
6350728b JMF |
1073 | for f in info_dict['requested_formats']: |
1074 | new_info = dict(info_dict) | |
1075 | new_info.update(f) | |
1076 | fname = self.prepare_filename(new_info) | |
1077 | fname = prepend_extension(fname, 'f%s' % f['format_id']) | |
1078 | downloaded.append(fname) | |
1079 | partial_success = dl(fname, new_info) | |
1080 | success = success and partial_success | |
58c3c7ae | 1081 | info_dict['__postprocessors'] = postprocessors |
6350728b JMF |
1082 | info_dict['__files_to_merge'] = downloaded |
1083 | else: | |
1084 | # Just a single file | |
1085 | success = dl(filename, info_dict) | |
8222d8de | 1086 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
6febd1c1 | 1087 | self.report_error('unable to download video data: %s' % str(err)) |
8222d8de | 1088 | return |
c40c6aaa JMF |
1089 | except (OSError, IOError) as err: |
1090 | raise UnavailableVideoError(err) | |
8222d8de | 1091 | except (ContentTooShortError, ) as err: |
6febd1c1 | 1092 | self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) |
8222d8de JMF |
1093 | return |
1094 | ||
1095 | if success: | |
1096 | try: | |
1097 | self.post_process(filename, info_dict) | |
1098 | except (PostProcessingError) as err: | |
6febd1c1 | 1099 | self.report_error('postprocessing: %s' % str(err)) |
8222d8de JMF |
1100 | return |
1101 | ||
c1c9a79c PH |
1102 | self.record_download_archive(info_dict) |
1103 | ||
8222d8de JMF |
1104 | def download(self, url_list): |
1105 | """Download a given list of URLs.""" | |
acd69589 | 1106 | outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) |
0c75c3fa | 1107 | if (len(url_list) > 1 and |
acd69589 | 1108 | '%' not in outtmpl |
0c75c3fa | 1109 | and self.params.get('max_downloads') != 1): |
acd69589 | 1110 | raise SameFileError(outtmpl) |
8222d8de JMF |
1111 | |
1112 | for url in url_list: | |
1113 | try: | |
1114 | #It also downloads the videos | |
63e0be34 | 1115 | res = self.extract_info(url) |
8222d8de | 1116 | except UnavailableVideoError: |
6febd1c1 | 1117 | self.report_error('unable to download video') |
8222d8de | 1118 | except MaxDownloadsReached: |
6febd1c1 | 1119 | self.to_screen('[info] Maximum number of downloaded files reached.') |
8222d8de | 1120 | raise |
63e0be34 PH |
1121 | else: |
1122 | if self.params.get('dump_single_json', False): | |
1123 | self.to_stdout(json.dumps(res)) | |
8222d8de JMF |
1124 | |
1125 | return self._download_retcode | |
1126 | ||
1dcc4c0c | 1127 | def download_with_info_file(self, info_filename): |
395293a8 | 1128 | with io.open(info_filename, 'r', encoding='utf-8') as f: |
1dcc4c0c | 1129 | info = json.load(f) |
d4943898 JMF |
1130 | try: |
1131 | self.process_ie_result(info, download=True) | |
1132 | except DownloadError: | |
1133 | webpage_url = info.get('webpage_url') | |
1134 | if webpage_url is not None: | |
6febd1c1 | 1135 | self.report_warning('The info failed to download, trying with "%s"' % webpage_url) |
d4943898 JMF |
1136 | return self.download([webpage_url]) |
1137 | else: | |
1138 | raise | |
1139 | return self._download_retcode | |
1dcc4c0c | 1140 | |
8222d8de JMF |
1141 | def post_process(self, filename, ie_info): |
1142 | """Run all the postprocessors on the given file.""" | |
1143 | info = dict(ie_info) | |
1144 | info['filepath'] = filename | |
1145 | keep_video = None | |
6350728b JMF |
1146 | pps_chain = [] |
1147 | if ie_info.get('__postprocessors') is not None: | |
1148 | pps_chain.extend(ie_info['__postprocessors']) | |
1149 | pps_chain.extend(self._pps) | |
1150 | for pp in pps_chain: | |
8222d8de | 1151 | try: |
fe7e0c98 | 1152 | keep_video_wish, new_info = pp.run(info) |
8222d8de JMF |
1153 | if keep_video_wish is not None: |
1154 | if keep_video_wish: | |
1155 | keep_video = keep_video_wish | |
1156 | elif keep_video is None: | |
1157 | # No clear decision yet, let IE decide | |
1158 | keep_video = keep_video_wish | |
1159 | except PostProcessingError as e: | |
bbcbf4d4 | 1160 | self.report_error(e.msg) |
8222d8de JMF |
1161 | if keep_video is False and not self.params.get('keepvideo', False): |
1162 | try: | |
6febd1c1 | 1163 | self.to_screen('Deleting original file %s (pass -k to keep)' % filename) |
8222d8de JMF |
1164 | os.remove(encodeFilename(filename)) |
1165 | except (IOError, OSError): | |
6febd1c1 | 1166 | self.report_warning('Unable to remove downloaded video file') |
c1c9a79c | 1167 | |
5db07df6 PH |
1168 | def _make_archive_id(self, info_dict): |
1169 | # Future-proof against any change in case | |
1170 | # and backwards compatibility with prior versions | |
d31209a1 | 1171 | extractor = info_dict.get('extractor_key') |
7012b23c PH |
1172 | if extractor is None: |
1173 | if 'id' in info_dict: | |
1174 | extractor = info_dict.get('ie_key') # key in a playlist | |
1175 | if extractor is None: | |
5db07df6 | 1176 | return None # Incomplete video information |
6febd1c1 | 1177 | return extractor.lower() + ' ' + info_dict['id'] |
5db07df6 PH |
1178 | |
1179 | def in_download_archive(self, info_dict): | |
1180 | fn = self.params.get('download_archive') | |
1181 | if fn is None: | |
1182 | return False | |
1183 | ||
1184 | vid_id = self._make_archive_id(info_dict) | |
1185 | if vid_id is None: | |
7012b23c | 1186 | return False # Incomplete video information |
5db07df6 | 1187 | |
c1c9a79c PH |
1188 | try: |
1189 | with locked_file(fn, 'r', encoding='utf-8') as archive_file: | |
1190 | for line in archive_file: | |
1191 | if line.strip() == vid_id: | |
1192 | return True | |
1193 | except IOError as ioe: | |
1194 | if ioe.errno != errno.ENOENT: | |
1195 | raise | |
1196 | return False | |
1197 | ||
1198 | def record_download_archive(self, info_dict): | |
1199 | fn = self.params.get('download_archive') | |
1200 | if fn is None: | |
1201 | return | |
5db07df6 PH |
1202 | vid_id = self._make_archive_id(info_dict) |
1203 | assert vid_id | |
c1c9a79c | 1204 | with locked_file(fn, 'a', encoding='utf-8') as archive_file: |
6febd1c1 | 1205 | archive_file.write(vid_id + '\n') |
dd82ffea | 1206 | |
8c51aa65 | 1207 | @staticmethod |
8abeeb94 | 1208 | def format_resolution(format, default='unknown'): |
fb04e403 PH |
1209 | if format.get('vcodec') == 'none': |
1210 | return 'audio only' | |
f49d89ee PH |
1211 | if format.get('resolution') is not None: |
1212 | return format['resolution'] | |
8c51aa65 JMF |
1213 | if format.get('height') is not None: |
1214 | if format.get('width') is not None: | |
6febd1c1 | 1215 | res = '%sx%s' % (format['width'], format['height']) |
8c51aa65 | 1216 | else: |
6febd1c1 | 1217 | res = '%sp' % format['height'] |
f49d89ee | 1218 | elif format.get('width') is not None: |
6febd1c1 | 1219 | res = '?x%d' % format['width'] |
8c51aa65 | 1220 | else: |
8abeeb94 | 1221 | res = default |
8c51aa65 JMF |
1222 | return res |
1223 | ||
c57f7757 PH |
1224 | def _format_note(self, fdict): |
1225 | res = '' | |
1226 | if fdict.get('ext') in ['f4f', 'f4m']: | |
1227 | res += '(unsupported) ' | |
1228 | if fdict.get('format_note') is not None: | |
1229 | res += fdict['format_note'] + ' ' | |
1230 | if fdict.get('tbr') is not None: | |
1231 | res += '%4dk ' % fdict['tbr'] | |
1232 | if fdict.get('container') is not None: | |
1233 | if res: | |
1234 | res += ', ' | |
1235 | res += '%s container' % fdict['container'] | |
1236 | if (fdict.get('vcodec') is not None and | |
1237 | fdict.get('vcodec') != 'none'): | |
1238 | if res: | |
1239 | res += ', ' | |
1240 | res += fdict['vcodec'] | |
91c7271a | 1241 | if fdict.get('vbr') is not None: |
c57f7757 PH |
1242 | res += '@' |
1243 | elif fdict.get('vbr') is not None and fdict.get('abr') is not None: | |
1244 | res += 'video@' | |
1245 | if fdict.get('vbr') is not None: | |
1246 | res += '%4dk' % fdict['vbr'] | |
fbb21cf5 PH |
1247 | if fdict.get('fps') is not None: |
1248 | res += ', %sfps' % fdict['fps'] | |
c57f7757 PH |
1249 | if fdict.get('acodec') is not None: |
1250 | if res: | |
1251 | res += ', ' | |
1252 | if fdict['acodec'] == 'none': | |
1253 | res += 'video only' | |
1254 | else: | |
1255 | res += '%-5s' % fdict['acodec'] | |
1256 | elif fdict.get('abr') is not None: | |
1257 | if res: | |
1258 | res += ', ' | |
1259 | res += 'audio' | |
1260 | if fdict.get('abr') is not None: | |
1261 | res += '@%3dk' % fdict['abr'] | |
1262 | if fdict.get('asr') is not None: | |
1263 | res += ' (%5dHz)' % fdict['asr'] | |
1264 | if fdict.get('filesize') is not None: | |
1265 | if res: | |
1266 | res += ', ' | |
1267 | res += format_bytes(fdict['filesize']) | |
9732d77e PH |
1268 | elif fdict.get('filesize_approx') is not None: |
1269 | if res: | |
1270 | res += ', ' | |
1271 | res += '~' + format_bytes(fdict['filesize_approx']) | |
c57f7757 | 1272 | return res |
91c7271a | 1273 | |
c57f7757 | 1274 | def list_formats(self, info_dict): |
02dbf93f | 1275 | def line(format, idlen=20): |
6febd1c1 | 1276 | return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % ( |
8c51aa65 JMF |
1277 | format['format_id'], |
1278 | format['ext'], | |
8c51aa65 | 1279 | self.format_resolution(format), |
c57f7757 | 1280 | self._format_note(format), |
02dbf93f | 1281 | )) |
57dd9a8f | 1282 | |
94badb25 | 1283 | formats = info_dict.get('formats', [info_dict]) |
6febd1c1 | 1284 | idlen = max(len('format code'), |
02dbf93f PH |
1285 | max(len(f['format_id']) for f in formats)) |
1286 | formats_s = [line(f, idlen) for f in formats] | |
94badb25 | 1287 | if len(formats) > 1: |
c57f7757 PH |
1288 | formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)' |
1289 | formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)' | |
57dd9a8f PH |
1290 | |
1291 | header_line = line({ | |
6febd1c1 PH |
1292 | 'format_id': 'format code', 'ext': 'extension', |
1293 | 'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen) | |
1294 | self.to_screen('[info] Available formats for %s:\n%s\n%s' % | |
1295 | (info_dict['id'], header_line, '\n'.join(formats_s))) | |
dca08720 PH |
1296 | |
1297 | def urlopen(self, req): | |
1298 | """ Start an HTTP download """ | |
37419b4f | 1299 | |
d05cfe06 S |
1300 | # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not |
1301 | # always respected by websites, some tend to give out URLs with non percent-encoded | |
1302 | # non-ASCII characters (see telemb.py, ard.py [#3412]) | |
37419b4f | 1303 | # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991) |
d05cfe06 S |
1304 | # To work around aforementioned issue we will replace request's original URL with |
1305 | # percent-encoded one | |
ee0d9070 | 1306 | req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str) |
68b09730 | 1307 | url = req if req_is_string else req.get_full_url() |
d05cfe06 | 1308 | url_escaped = escape_url(url) |
37419b4f S |
1309 | |
1310 | # Substitute URL if any change after escaping | |
1311 | if url != url_escaped: | |
68b09730 | 1312 | if req_is_string: |
37419b4f S |
1313 | req = url_escaped |
1314 | else: | |
1315 | req = compat_urllib_request.Request( | |
1316 | url_escaped, data=req.data, headers=req.headers, | |
1317 | origin_req_host=req.origin_req_host, unverifiable=req.unverifiable) | |
1318 | ||
19a41fc6 | 1319 | return self._opener.open(req, timeout=self._socket_timeout) |
dca08720 PH |
1320 | |
1321 | def print_debug_header(self): | |
1322 | if not self.params.get('verbose'): | |
1323 | return | |
62fec3b2 | 1324 | |
4192b51c PH |
1325 | if type('') is not compat_str: |
1326 | # Python 2.6 on SLES11 SP1 (https://github.com/rg3/youtube-dl/issues/3326) | |
1327 | self.report_warning( | |
1328 | 'Your Python is broken! Update to a newer and supported version') | |
1329 | ||
c6afed48 PH |
1330 | stdout_encoding = getattr( |
1331 | sys.stdout, 'encoding', 'missing (%s)' % type(sys.stdout).__name__) | |
b0472057 | 1332 | encoding_str = ( |
734f90bb PH |
1333 | '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( |
1334 | locale.getpreferredencoding(), | |
1335 | sys.getfilesystemencoding(), | |
c6afed48 | 1336 | stdout_encoding, |
b0472057 | 1337 | self.get_encoding())) |
4192b51c | 1338 | write_string(encoding_str, encoding=None) |
734f90bb PH |
1339 | |
1340 | self._write_string('[debug] youtube-dl version ' + __version__ + '\n') | |
dca08720 PH |
1341 | try: |
1342 | sp = subprocess.Popen( | |
1343 | ['git', 'rev-parse', '--short', 'HEAD'], | |
1344 | stdout=subprocess.PIPE, stderr=subprocess.PIPE, | |
1345 | cwd=os.path.dirname(os.path.abspath(__file__))) | |
1346 | out, err = sp.communicate() | |
1347 | out = out.decode().strip() | |
1348 | if re.match('[0-9a-f]+', out): | |
734f90bb | 1349 | self._write_string('[debug] Git HEAD: ' + out + '\n') |
dca08720 PH |
1350 | except: |
1351 | try: | |
1352 | sys.exc_clear() | |
1353 | except: | |
1354 | pass | |
d28b5171 PH |
1355 | self._write_string('[debug] Python version %s - %s\n' % ( |
1356 | platform.python_version(), platform_name())) | |
1357 | ||
1358 | exe_versions = FFmpegPostProcessor.get_versions() | |
4c83c967 | 1359 | exe_versions['rtmpdump'] = rtmpdump_version() |
d28b5171 PH |
1360 | exe_str = ', '.join( |
1361 | '%s %s' % (exe, v) | |
1362 | for exe, v in sorted(exe_versions.items()) | |
1363 | if v | |
1364 | ) | |
1365 | if not exe_str: | |
1366 | exe_str = 'none' | |
1367 | self._write_string('[debug] exe versions: %s\n' % exe_str) | |
dca08720 PH |
1368 | |
1369 | proxy_map = {} | |
1370 | for handler in self._opener.handlers: | |
1371 | if hasattr(handler, 'proxies'): | |
1372 | proxy_map.update(handler.proxies) | |
734f90bb | 1373 | self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n') |
dca08720 | 1374 | |
e344693b | 1375 | def _setup_opener(self): |
6ad14cab | 1376 | timeout_val = self.params.get('socket_timeout') |
19a41fc6 | 1377 | self._socket_timeout = 600 if timeout_val is None else float(timeout_val) |
6ad14cab | 1378 | |
dca08720 PH |
1379 | opts_cookiefile = self.params.get('cookiefile') |
1380 | opts_proxy = self.params.get('proxy') | |
1381 | ||
1382 | if opts_cookiefile is None: | |
1383 | self.cookiejar = compat_cookiejar.CookieJar() | |
1384 | else: | |
1385 | self.cookiejar = compat_cookiejar.MozillaCookieJar( | |
1386 | opts_cookiefile) | |
1387 | if os.access(opts_cookiefile, os.R_OK): | |
1388 | self.cookiejar.load() | |
1389 | ||
1390 | cookie_processor = compat_urllib_request.HTTPCookieProcessor( | |
1391 | self.cookiejar) | |
1392 | if opts_proxy is not None: | |
1393 | if opts_proxy == '': | |
1394 | proxies = {} | |
1395 | else: | |
1396 | proxies = {'http': opts_proxy, 'https': opts_proxy} | |
1397 | else: | |
1398 | proxies = compat_urllib_request.getproxies() | |
1399 | # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805) | |
1400 | if 'http' in proxies and 'https' not in proxies: | |
1401 | proxies['https'] = proxies['http'] | |
1402 | proxy_handler = compat_urllib_request.ProxyHandler(proxies) | |
a0ddb8a2 PH |
1403 | |
1404 | debuglevel = 1 if self.params.get('debug_printtraffic') else 0 | |
dca08720 | 1405 | https_handler = make_HTTPS_handler( |
a0ddb8a2 PH |
1406 | self.params.get('nocheckcertificate', False), debuglevel=debuglevel) |
1407 | ydlh = YoutubeDLHandler(debuglevel=debuglevel) | |
dca08720 | 1408 | opener = compat_urllib_request.build_opener( |
a0ddb8a2 | 1409 | https_handler, proxy_handler, cookie_processor, ydlh) |
dca08720 PH |
1410 | # Delete the default user-agent header, which would otherwise apply in |
1411 | # cases where our custom HTTP handler doesn't come into play | |
1412 | # (See https://github.com/rg3/youtube-dl/issues/1309 for details) | |
1413 | opener.addheaders = [] | |
1414 | self._opener = opener | |
62fec3b2 PH |
1415 | |
1416 | def encode(self, s): | |
1417 | if isinstance(s, bytes): | |
1418 | return s # Already encoded | |
1419 | ||
1420 | try: | |
1421 | return s.encode(self.get_encoding()) | |
1422 | except UnicodeEncodeError as err: | |
1423 | err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.' | |
1424 | raise | |
1425 | ||
1426 | def get_encoding(self): | |
1427 | encoding = self.params.get('encoding') | |
1428 | if encoding is None: | |
1429 | encoding = preferredencoding() | |
1430 | return encoding | |
7d4111ed | 1431 |