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