]>
Commit | Line | Data |
---|---|---|
f1a9d64e PH |
1 | from __future__ import unicode_literals |
2 | ||
d6983cb4 | 3 | import base64 |
f4b1c7ad | 4 | import datetime |
3ec05685 | 5 | import hashlib |
3d3538e4 | 6 | import json |
4094b6e3 | 7 | import netrc |
d6983cb4 PH |
8 | import os |
9 | import re | |
10 | import socket | |
11 | import sys | |
4094b6e3 | 12 | import time |
267ed0c5 | 13 | import xml.etree.ElementTree |
d6983cb4 | 14 | |
8c25f81b | 15 | from ..compat import ( |
42939b61 | 16 | compat_cookiejar, |
96a53167 | 17 | compat_HTTPError, |
d6983cb4 PH |
18 | compat_http_client, |
19 | compat_urllib_error, | |
c7deaa4c | 20 | compat_urllib_parse_urlparse, |
f0b5d6af | 21 | compat_urlparse, |
d6983cb4 | 22 | compat_str, |
8c25f81b PH |
23 | ) |
24 | from ..utils import ( | |
05900629 | 25 | age_restricted, |
d6983cb4 PH |
26 | clean_html, |
27 | compiled_regex_type, | |
28 | ExtractorError, | |
b14f3a4c | 29 | float_or_none, |
96a53167 | 30 | HEADRequest, |
31bb8d3f | 31 | int_or_none, |
55b3e45b | 32 | RegexNotFoundError, |
d41e6efc | 33 | sanitize_filename, |
f38de77f | 34 | unescapeHTML, |
d6983cb4 | 35 | ) |
46374a56 | 36 | _NO_DEFAULT = object() |
d6983cb4 | 37 | |
dca08720 | 38 | |
d6983cb4 PH |
39 | class InfoExtractor(object): |
40 | """Information Extractor class. | |
41 | ||
42 | Information extractors are the classes that, given a URL, extract | |
43 | information about the video (or videos) the URL refers to. This | |
44 | information includes the real video URL, the video title, author and | |
45 | others. The information is stored in a dictionary which is then | |
5d380852 | 46 | passed to the YoutubeDL. The YoutubeDL processes this |
d6983cb4 PH |
47 | information possibly downloading the video to the file system, among |
48 | other possible outcomes. | |
49 | ||
fed5d032 PH |
50 | The type field determines the the type of the result. |
51 | By far the most common value (and the default if _type is missing) is | |
52 | "video", which indicates a single video. | |
53 | ||
54 | For a video, the dictionaries must include the following fields: | |
d6983cb4 PH |
55 | |
56 | id: Video identifier. | |
d6983cb4 | 57 | title: Video title, unescaped. |
d67b0b15 | 58 | |
f49d89ee | 59 | Additionally, it must contain either a formats entry or a url one: |
d67b0b15 | 60 | |
f49d89ee PH |
61 | formats: A list of dictionaries for each format available, ordered |
62 | from worst to best quality. | |
63 | ||
64 | Potential fields: | |
d67b0b15 PH |
65 | * url Mandatory. The URL of the video file |
66 | * ext Will be calculated from url if missing | |
67 | * format A human-readable description of the format | |
68 | ("mp4 container with h264/opus"). | |
69 | Calculated from the format_id, width, height. | |
70 | and format_note fields if missing. | |
71 | * format_id A short description of the format | |
5d4f3985 PH |
72 | ("mp4_h264_opus" or "19"). |
73 | Technically optional, but strongly recommended. | |
d67b0b15 PH |
74 | * format_note Additional info about the format |
75 | ("3D" or "DASH video") | |
76 | * width Width of the video, if known | |
77 | * height Height of the video, if known | |
f49d89ee | 78 | * resolution Textual description of width and height |
7217e148 | 79 | * tbr Average bitrate of audio and video in KBit/s |
d67b0b15 PH |
80 | * abr Average audio bitrate in KBit/s |
81 | * acodec Name of the audio codec in use | |
dd27fd17 | 82 | * asr Audio sampling rate in Hertz |
d67b0b15 | 83 | * vbr Average video bitrate in KBit/s |
fbb21cf5 | 84 | * fps Frame rate |
d67b0b15 | 85 | * vcodec Name of the video codec in use |
1394ce65 | 86 | * container Name of the container format |
d67b0b15 | 87 | * filesize The number of bytes, if known in advance |
9732d77e | 88 | * filesize_approx An estimate for the number of bytes |
d67b0b15 | 89 | * player_url SWF Player URL (used for rtmpdump). |
c7deaa4c PH |
90 | * protocol The protocol that will be used for the actual |
91 | download, lower-case. | |
b04b8852 PH |
92 | "http", "https", "rtsp", "rtmp", "rtmpe", |
93 | "m3u8", or "m3u8_native". | |
f49d89ee | 94 | * preference Order number of this format. If this field is |
08d13955 | 95 | present and not None, the formats get sorted |
38d63d84 | 96 | by this field, regardless of all other values. |
f49d89ee PH |
97 | -1 for default (order by other properties), |
98 | -2 or smaller for less than default. | |
e65566a9 PH |
99 | < -1000 to hide the format (if there is |
100 | another one which is strictly better) | |
aff2f4f4 PH |
101 | * language_preference Is this in the correct requested |
102 | language? | |
103 | 10 if it's what the URL is about, | |
104 | -1 for default (don't know), | |
105 | -10 otherwise, other values reserved for now. | |
5d73273f PH |
106 | * quality Order number of the video quality of this |
107 | format, irrespective of the file format. | |
108 | -1 for default (order by other properties), | |
109 | -2 or smaller for less than default. | |
c64ed2a3 PH |
110 | * source_preference Order number for this video source |
111 | (quality takes higher priority) | |
112 | -1 for default (order by other properties), | |
113 | -2 or smaller for less than default. | |
d769be6c PH |
114 | * http_method HTTP method to use for the download. |
115 | * http_headers A dictionary of additional HTTP headers | |
116 | to add to the request. | |
117 | * http_post_data Additional data to send with a POST | |
118 | request. | |
6271f1ca | 119 | * stretched_ratio If given and not 1, indicates that the |
3dee7826 PH |
120 | video's pixels are not square. |
121 | width : height ratio as float. | |
122 | * no_resume The server does not support resuming the | |
123 | (HTTP or RTMP) download. Boolean. | |
124 | ||
c0ba0f48 | 125 | url: Final video URL. |
d6983cb4 | 126 | ext: Video filename extension. |
d67b0b15 PH |
127 | format: The video format, defaults to ext (used for --get-format) |
128 | player_url: SWF Player URL (used for rtmpdump). | |
2f5865cc | 129 | |
d6983cb4 PH |
130 | The following fields are optional: |
131 | ||
f5e43bc6 | 132 | alt_title: A secondary title of the video. |
0afef30b PH |
133 | display_id An alternative identifier for the video, not necessarily |
134 | unique, but available before title. Typically, id is | |
135 | something like "4234987", title "Dancing naked mole rats", | |
136 | and display_id "dancing-naked-mole-rats" | |
d5519808 | 137 | thumbnails: A list of dictionaries, with the following entries: |
cfb56d1a | 138 | * "id" (optional, string) - Thumbnail format ID |
d5519808 | 139 | * "url" |
cfb56d1a | 140 | * "preference" (optional, int) - quality of the image |
d5519808 PH |
141 | * "width" (optional, int) |
142 | * "height" (optional, int) | |
143 | * "resolution" (optional, string "{width}x{height"}, | |
144 | deprecated) | |
d6983cb4 | 145 | thumbnail: Full URL to a video thumbnail image. |
f5e43bc6 | 146 | description: Full video description. |
d6983cb4 | 147 | uploader: Full name of the video uploader. |
9bb8e0a3 | 148 | creator: The main artist who created the video. |
955c4514 | 149 | timestamp: UNIX timestamp of the moment the video became available. |
d6983cb4 | 150 | upload_date: Video upload date (YYYYMMDD). |
955c4514 | 151 | If not explicitly set, calculated from timestamp. |
d6983cb4 | 152 | uploader_id: Nickname or id of the video uploader. |
da9ec3b9 | 153 | location: Physical location where the video was filmed. |
5d51a883 JMF |
154 | subtitles: The subtitle file contents as a dictionary in the format |
155 | {language: subtitles}. | |
c0ba0f48 | 156 | duration: Length of the video in seconds, as an integer. |
f3d29461 | 157 | view_count: How many users have watched the video on the platform. |
19e3dfc9 PH |
158 | like_count: Number of positive ratings of the video |
159 | dislike_count: Number of negative ratings of the video | |
2d30521a | 160 | average_rating: Average rating give by users, the scale used depends on the webpage |
19e3dfc9 | 161 | comment_count: Number of comments on the video |
dd622d7c PH |
162 | comments: A list of comments, each with one or more of the following |
163 | properties (all but one of text or html optional): | |
164 | * "author" - human-readable name of the comment author | |
165 | * "author_id" - user ID of the comment author | |
166 | * "id" - Comment ID | |
167 | * "html" - Comment as HTML | |
168 | * "text" - Plain text of the comment | |
169 | * "timestamp" - UNIX timestamp of comment | |
170 | * "parent" - ID of the comment this one is replying to. | |
171 | Set to "root" to indicate that this is a | |
172 | comment to the original video. | |
8dbe9899 | 173 | age_limit: Age restriction for the video, as an integer (years) |
9103bbc5 JMF |
174 | webpage_url: The url to the video webpage, if given to youtube-dl it |
175 | should allow to get the same result again. (It will be set | |
176 | by YoutubeDL if it's missing) | |
ad3bc6ac PH |
177 | categories: A list of categories that the video falls in, for example |
178 | ["Sports", "Berlin"] | |
7267bd53 PH |
179 | is_live: True, False, or None (=unknown). Whether this video is a |
180 | live stream that goes on instead of a fixed-length video. | |
d6983cb4 | 181 | |
deefc05b | 182 | Unless mentioned otherwise, the fields should be Unicode strings. |
d6983cb4 | 183 | |
d838b1bd PH |
184 | Unless mentioned otherwise, None is equivalent to absence of information. |
185 | ||
fed5d032 PH |
186 | |
187 | _type "playlist" indicates multiple videos. | |
b82f815f PH |
188 | There must be a key "entries", which is a list, an iterable, or a PagedList |
189 | object, each element of which is a valid dictionary by this specification. | |
fed5d032 PH |
190 | |
191 | Additionally, playlists can have "title" and "id" attributes with the same | |
192 | semantics as videos (see above). | |
193 | ||
194 | ||
195 | _type "multi_video" indicates that there are multiple videos that | |
196 | form a single show, for examples multiple acts of an opera or TV episode. | |
197 | It must have an entries key like a playlist and contain all the keys | |
198 | required for a video at the same time. | |
199 | ||
200 | ||
201 | _type "url" indicates that the video must be extracted from another | |
202 | location, possibly by a different extractor. Its only required key is: | |
203 | "url" - the next URL to extract. | |
f58766ce PH |
204 | The key "ie_key" can be set to the class name (minus the trailing "IE", |
205 | e.g. "Youtube") if the extractor class is known in advance. | |
206 | Additionally, the dictionary may have any properties of the resolved entity | |
207 | known in advance, for example "title" if the title of the referred video is | |
fed5d032 PH |
208 | known ahead of time. |
209 | ||
210 | ||
211 | _type "url_transparent" entities have the same specification as "url", but | |
212 | indicate that the given additional information is more precise than the one | |
213 | associated with the resolved URL. | |
214 | This is useful when a site employs a video service that hosts the video and | |
215 | its technical metadata, but that video service does not embed a useful | |
216 | title, description etc. | |
217 | ||
218 | ||
d6983cb4 PH |
219 | Subclasses of this one should re-define the _real_initialize() and |
220 | _real_extract() methods and define a _VALID_URL regexp. | |
221 | Probably, they should also be added to the list of extractors. | |
222 | ||
d6983cb4 PH |
223 | Finally, the _WORKING attribute should be set to False for broken IEs |
224 | in order to warn the users and skip the tests. | |
225 | """ | |
226 | ||
227 | _ready = False | |
228 | _downloader = None | |
229 | _WORKING = True | |
230 | ||
231 | def __init__(self, downloader=None): | |
232 | """Constructor. Receives an optional downloader.""" | |
233 | self._ready = False | |
234 | self.set_downloader(downloader) | |
235 | ||
236 | @classmethod | |
237 | def suitable(cls, url): | |
238 | """Receives a URL and returns True if suitable for this IE.""" | |
79cb2577 PH |
239 | |
240 | # This does not use has/getattr intentionally - we want to know whether | |
241 | # we have cached the regexp for *this* class, whereas getattr would also | |
242 | # match the superclass | |
243 | if '_VALID_URL_RE' not in cls.__dict__: | |
244 | cls._VALID_URL_RE = re.compile(cls._VALID_URL) | |
245 | return cls._VALID_URL_RE.match(url) is not None | |
d6983cb4 | 246 | |
ed9266db PH |
247 | @classmethod |
248 | def _match_id(cls, url): | |
249 | if '_VALID_URL_RE' not in cls.__dict__: | |
250 | cls._VALID_URL_RE = re.compile(cls._VALID_URL) | |
251 | m = cls._VALID_URL_RE.match(url) | |
252 | assert m | |
253 | return m.group('id') | |
254 | ||
d6983cb4 PH |
255 | @classmethod |
256 | def working(cls): | |
257 | """Getter method for _WORKING.""" | |
258 | return cls._WORKING | |
259 | ||
260 | def initialize(self): | |
261 | """Initializes an instance (authentication, etc).""" | |
262 | if not self._ready: | |
263 | self._real_initialize() | |
264 | self._ready = True | |
265 | ||
266 | def extract(self, url): | |
267 | """Extracts URL information and returns it in list of dicts.""" | |
3a5bcd03 PH |
268 | try: |
269 | self.initialize() | |
270 | return self._real_extract(url) | |
271 | except ExtractorError: | |
272 | raise | |
273 | except compat_http_client.IncompleteRead as e: | |
274 | raise ExtractorError('A network error has occured.', cause=e, expected=True) | |
9650885b | 275 | except (KeyError, StopIteration) as e: |
3a5bcd03 | 276 | raise ExtractorError('An extractor error has occured.', cause=e) |
d6983cb4 PH |
277 | |
278 | def set_downloader(self, downloader): | |
279 | """Sets the downloader for this IE.""" | |
280 | self._downloader = downloader | |
281 | ||
282 | def _real_initialize(self): | |
283 | """Real initialization process. Redefine in subclasses.""" | |
284 | pass | |
285 | ||
286 | def _real_extract(self, url): | |
287 | """Real extraction process. Redefine in subclasses.""" | |
288 | pass | |
289 | ||
56c73665 JMF |
290 | @classmethod |
291 | def ie_key(cls): | |
292 | """A string for getting the InfoExtractor with get_info_extractor""" | |
293 | return cls.__name__[:-2] | |
294 | ||
d6983cb4 PH |
295 | @property |
296 | def IE_NAME(self): | |
297 | return type(self).__name__[:-2] | |
298 | ||
7cc3570e | 299 | def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): |
d6983cb4 PH |
300 | """ Returns the response handle """ |
301 | if note is None: | |
302 | self.report_download_webpage(video_id) | |
303 | elif note is not False: | |
7cc3570e | 304 | if video_id is None: |
f1a9d64e | 305 | self.to_screen('%s' % (note,)) |
7cc3570e | 306 | else: |
f1a9d64e | 307 | self.to_screen('%s: %s' % (video_id, note)) |
d6983cb4 | 308 | try: |
dca08720 | 309 | return self._downloader.urlopen(url_or_request) |
d6983cb4 | 310 | except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: |
aa94a6d3 PH |
311 | if errnote is False: |
312 | return False | |
d6983cb4 | 313 | if errnote is None: |
f1a9d64e PH |
314 | errnote = 'Unable to download webpage' |
315 | errmsg = '%s: %s' % (errnote, compat_str(err)) | |
7cc3570e PH |
316 | if fatal: |
317 | raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) | |
318 | else: | |
319 | self._downloader.report_warning(errmsg) | |
320 | return False | |
d6983cb4 | 321 | |
7cc3570e | 322 | def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True): |
d6983cb4 | 323 | """ Returns a tuple (page content as string, URL handle) """ |
b9d3e163 PH |
324 | # Strip hashes from the URL (#1038) |
325 | if isinstance(url_or_request, (compat_str, str)): | |
326 | url_or_request = url_or_request.partition('#')[0] | |
327 | ||
7cc3570e PH |
328 | urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) |
329 | if urlh is False: | |
330 | assert not fatal | |
331 | return False | |
23be51d8 PH |
332 | content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal) |
333 | return (content, urlh) | |
334 | ||
4e262a88 | 335 | def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None): |
d6983cb4 | 336 | content_type = urlh.headers.get('Content-Type', '') |
f143d86a | 337 | webpage_bytes = urlh.read() |
4e262a88 PH |
338 | if prefix is not None: |
339 | webpage_bytes = prefix + webpage_bytes | |
d6983cb4 PH |
340 | m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) |
341 | if m: | |
342 | encoding = m.group(1) | |
343 | else: | |
0d75ae2c | 344 | m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]', |
f143d86a PH |
345 | webpage_bytes[:1024]) |
346 | if m: | |
347 | encoding = m.group(1).decode('ascii') | |
b60016e8 PH |
348 | elif webpage_bytes.startswith(b'\xff\xfe'): |
349 | encoding = 'utf-16' | |
f143d86a PH |
350 | else: |
351 | encoding = 'utf-8' | |
d6983cb4 PH |
352 | if self._downloader.params.get('dump_intermediate_pages', False): |
353 | try: | |
354 | url = url_or_request.get_full_url() | |
355 | except AttributeError: | |
356 | url = url_or_request | |
f1a9d64e | 357 | self.to_screen('Dumping request to ' + url) |
d6983cb4 PH |
358 | dump = base64.b64encode(webpage_bytes).decode('ascii') |
359 | self._downloader.to_screen(dump) | |
d41e6efc PH |
360 | if self._downloader.params.get('write_pages', False): |
361 | try: | |
362 | url = url_or_request.get_full_url() | |
363 | except AttributeError: | |
364 | url = url_or_request | |
5afa7f8b | 365 | basen = '%s_%s' % (video_id, url) |
c1bce22f | 366 | if len(basen) > 240: |
f1a9d64e | 367 | h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest() |
c1bce22f PH |
368 | basen = basen[:240 - len(h)] + h |
369 | raw_filename = basen + '.dump' | |
d41e6efc | 370 | filename = sanitize_filename(raw_filename, restricted=True) |
f1a9d64e | 371 | self.to_screen('Saving request to ' + filename) |
5f58165d S |
372 | # Working around MAX_PATH limitation on Windows (see |
373 | # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx) | |
374 | if os.name == 'nt': | |
375 | absfilepath = os.path.abspath(filename) | |
376 | if len(absfilepath) > 259: | |
377 | filename = '\\\\?\\' + absfilepath | |
d41e6efc PH |
378 | with open(filename, 'wb') as outf: |
379 | outf.write(webpage_bytes) | |
380 | ||
ec0fafbb AA |
381 | try: |
382 | content = webpage_bytes.decode(encoding, 'replace') | |
383 | except LookupError: | |
384 | content = webpage_bytes.decode('utf-8', 'replace') | |
2410c43d | 385 | |
f1a9d64e PH |
386 | if ('<title>Access to this site is blocked</title>' in content and |
387 | 'Websense' in content[:512]): | |
388 | msg = 'Access to this webpage has been blocked by Websense filtering software in your network.' | |
2410c43d PH |
389 | blocked_iframe = self._html_search_regex( |
390 | r'<iframe src="([^"]+)"', content, | |
f1a9d64e | 391 | 'Websense information URL', default=None) |
2410c43d | 392 | if blocked_iframe: |
f1a9d64e | 393 | msg += ' Visit %s for more details' % blocked_iframe |
2410c43d PH |
394 | raise ExtractorError(msg, expected=True) |
395 | ||
23be51d8 | 396 | return content |
d6983cb4 | 397 | |
995ad69c | 398 | def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5): |
d6983cb4 | 399 | """ Returns the data of the page as a string """ |
995ad69c TF |
400 | success = False |
401 | try_count = 0 | |
402 | while success is False: | |
403 | try: | |
404 | res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) | |
405 | success = True | |
406 | except compat_http_client.IncompleteRead as e: | |
407 | try_count += 1 | |
408 | if try_count >= tries: | |
409 | raise e | |
410 | self._sleep(timeout, video_id) | |
7cc3570e PH |
411 | if res is False: |
412 | return res | |
413 | else: | |
414 | content, _ = res | |
415 | return content | |
d6983cb4 | 416 | |
2a275ab0 | 417 | def _download_xml(self, url_or_request, video_id, |
f1a9d64e | 418 | note='Downloading XML', errnote='Unable to download XML', |
28746fbd | 419 | transform_source=None, fatal=True): |
267ed0c5 | 420 | """Return the xml as an xml.etree.ElementTree.Element""" |
28746fbd PH |
421 | xml_string = self._download_webpage( |
422 | url_or_request, video_id, note, errnote, fatal=fatal) | |
423 | if xml_string is False: | |
424 | return xml_string | |
e2b38da9 PH |
425 | if transform_source: |
426 | xml_string = transform_source(xml_string) | |
267ed0c5 JMF |
427 | return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) |
428 | ||
3d3538e4 | 429 | def _download_json(self, url_or_request, video_id, |
f1a9d64e PH |
430 | note='Downloading JSON metadata', |
431 | errnote='Unable to download JSON metadata', | |
b090af59 PH |
432 | transform_source=None, |
433 | fatal=True): | |
434 | json_string = self._download_webpage( | |
435 | url_or_request, video_id, note, errnote, fatal=fatal) | |
436 | if (not fatal) and json_string is False: | |
437 | return None | |
ebb64199 TF |
438 | return self._parse_json( |
439 | json_string, video_id, transform_source=transform_source, fatal=fatal) | |
440 | ||
441 | def _parse_json(self, json_string, video_id, transform_source=None, fatal=True): | |
81c2f20b PH |
442 | if transform_source: |
443 | json_string = transform_source(json_string) | |
3d3538e4 PH |
444 | try: |
445 | return json.loads(json_string) | |
446 | except ValueError as ve: | |
e7b6d122 PH |
447 | errmsg = '%s: Failed to parse JSON ' % video_id |
448 | if fatal: | |
449 | raise ExtractorError(errmsg, cause=ve) | |
450 | else: | |
451 | self.report_warning(errmsg + str(ve)) | |
3d3538e4 | 452 | |
f45f96f8 | 453 | def report_warning(self, msg, video_id=None): |
f1a9d64e | 454 | idstr = '' if video_id is None else '%s: ' % video_id |
f45f96f8 | 455 | self._downloader.report_warning( |
f1a9d64e | 456 | '[%s] %s%s' % (self.IE_NAME, idstr, msg)) |
f45f96f8 | 457 | |
d6983cb4 PH |
458 | def to_screen(self, msg): |
459 | """Print msg to screen, prefixing it with '[ie_name]'""" | |
f1a9d64e | 460 | self._downloader.to_screen('[%s] %s' % (self.IE_NAME, msg)) |
d6983cb4 PH |
461 | |
462 | def report_extraction(self, id_or_name): | |
463 | """Report information extraction.""" | |
f1a9d64e | 464 | self.to_screen('%s: Extracting information' % id_or_name) |
d6983cb4 PH |
465 | |
466 | def report_download_webpage(self, video_id): | |
467 | """Report webpage download.""" | |
f1a9d64e | 468 | self.to_screen('%s: Downloading webpage' % video_id) |
d6983cb4 PH |
469 | |
470 | def report_age_confirmation(self): | |
471 | """Report attempt to confirm age.""" | |
f1a9d64e | 472 | self.to_screen('Confirming age') |
d6983cb4 | 473 | |
fc79158d JMF |
474 | def report_login(self): |
475 | """Report attempt to log in.""" | |
f1a9d64e | 476 | self.to_screen('Logging in') |
fc79158d | 477 | |
5f6a1245 | 478 | # Methods for following #608 |
c0d0b01f JMF |
479 | @staticmethod |
480 | def url_result(url, ie=None, video_id=None): | |
d6983cb4 | 481 | """Returns a url that points to a page that should be processed""" |
5f6a1245 | 482 | # TODO: ie should be the class used for getting the info |
d6983cb4 PH |
483 | video_info = {'_type': 'url', |
484 | 'url': url, | |
485 | 'ie_key': ie} | |
7012b23c PH |
486 | if video_id is not None: |
487 | video_info['id'] = video_id | |
d6983cb4 | 488 | return video_info |
5f6a1245 | 489 | |
c0d0b01f | 490 | @staticmethod |
acf5cbfe | 491 | def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None): |
d6983cb4 PH |
492 | """Returns a playlist""" |
493 | video_info = {'_type': 'playlist', | |
494 | 'entries': entries} | |
495 | if playlist_id: | |
496 | video_info['id'] = playlist_id | |
497 | if playlist_title: | |
498 | video_info['title'] = playlist_title | |
acf5cbfe S |
499 | if playlist_description: |
500 | video_info['description'] = playlist_description | |
d6983cb4 PH |
501 | return video_info |
502 | ||
711ede6e | 503 | def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): |
d6983cb4 PH |
504 | """ |
505 | Perform a regex search on the given string, using a single or a list of | |
506 | patterns returning the first matching group. | |
507 | In case of failure return a default value or raise a WARNING or a | |
55b3e45b | 508 | RegexNotFoundError, depending on fatal, specifying the field name. |
d6983cb4 PH |
509 | """ |
510 | if isinstance(pattern, (str, compat_str, compiled_regex_type)): | |
511 | mobj = re.search(pattern, string, flags) | |
512 | else: | |
513 | for p in pattern: | |
514 | mobj = re.search(p, string, flags) | |
c3415d1b PH |
515 | if mobj: |
516 | break | |
d6983cb4 | 517 | |
7e5db8c9 | 518 | if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty(): |
f1a9d64e | 519 | _name = '\033[0;34m%s\033[0m' % name |
d6983cb4 PH |
520 | else: |
521 | _name = name | |
522 | ||
523 | if mobj: | |
711ede6e PH |
524 | if group is None: |
525 | # return the first matching group | |
526 | return next(g for g in mobj.groups() if g is not None) | |
527 | else: | |
528 | return mobj.group(group) | |
46374a56 | 529 | elif default is not _NO_DEFAULT: |
d6983cb4 PH |
530 | return default |
531 | elif fatal: | |
f1a9d64e | 532 | raise RegexNotFoundError('Unable to extract %s' % _name) |
d6983cb4 | 533 | else: |
f1a9d64e | 534 | self._downloader.report_warning('unable to extract %s; ' |
9e1a5b84 | 535 | 'please report this issue on http://yt-dl.org/bug' % _name) |
d6983cb4 PH |
536 | return None |
537 | ||
711ede6e | 538 | def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): |
d6983cb4 PH |
539 | """ |
540 | Like _search_regex, but strips HTML tags and unescapes entities. | |
541 | """ | |
711ede6e | 542 | res = self._search_regex(pattern, string, name, default, fatal, flags, group) |
d6983cb4 PH |
543 | if res: |
544 | return clean_html(res).strip() | |
545 | else: | |
546 | return res | |
547 | ||
fc79158d JMF |
548 | def _get_login_info(self): |
549 | """ | |
550 | Get the the login info as (username, password) | |
551 | It will look in the netrc file using the _NETRC_MACHINE value | |
552 | If there's no info available, return (None, None) | |
553 | """ | |
554 | if self._downloader is None: | |
555 | return (None, None) | |
556 | ||
557 | username = None | |
558 | password = None | |
559 | downloader_params = self._downloader.params | |
560 | ||
561 | # Attempt to use provided username and password or .netrc data | |
562 | if downloader_params.get('username', None) is not None: | |
563 | username = downloader_params['username'] | |
564 | password = downloader_params['password'] | |
565 | elif downloader_params.get('usenetrc', False): | |
566 | try: | |
567 | info = netrc.netrc().authenticators(self._NETRC_MACHINE) | |
568 | if info is not None: | |
569 | username = info[0] | |
570 | password = info[2] | |
571 | else: | |
572 | raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) | |
573 | except (IOError, netrc.NetrcParseError) as err: | |
f1a9d64e | 574 | self._downloader.report_warning('parsing .netrc: %s' % compat_str(err)) |
5f6a1245 | 575 | |
fc79158d JMF |
576 | return (username, password) |
577 | ||
83317f69 | 578 | def _get_tfa_info(self): |
579 | """ | |
580 | Get the two-factor authentication info | |
581 | TODO - asking the user will be required for sms/phone verify | |
582 | currently just uses the command line option | |
583 | If there's no info available, return None | |
584 | """ | |
585 | if self._downloader is None: | |
83317f69 | 586 | return None |
587 | downloader_params = self._downloader.params | |
588 | ||
589 | if downloader_params.get('twofactor', None) is not None: | |
590 | return downloader_params['twofactor'] | |
591 | ||
83317f69 | 592 | return None |
593 | ||
46720279 JMF |
594 | # Helper functions for extracting OpenGraph info |
595 | @staticmethod | |
ab2d5247 | 596 | def _og_regexes(prop): |
c1206423 | 597 | content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')' |
9887c9b2 | 598 | property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop) |
78fb87b2 | 599 | template = r'<meta[^>]+?%s[^>]+?%s' |
ab2d5247 | 600 | return [ |
78fb87b2 JMF |
601 | template % (property_re, content_re), |
602 | template % (content_re, property_re), | |
ab2d5247 | 603 | ] |
46720279 | 604 | |
3c4e6d83 | 605 | def _og_search_property(self, prop, html, name=None, **kargs): |
46720279 | 606 | if name is None: |
3c4e6d83 | 607 | name = 'OpenGraph %s' % prop |
ab2d5247 | 608 | escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs) |
eb0a8398 PH |
609 | if escaped is None: |
610 | return None | |
611 | return unescapeHTML(escaped) | |
46720279 JMF |
612 | |
613 | def _og_search_thumbnail(self, html, **kargs): | |
f1a9d64e | 614 | return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs) |
46720279 JMF |
615 | |
616 | def _og_search_description(self, html, **kargs): | |
617 | return self._og_search_property('description', html, fatal=False, **kargs) | |
618 | ||
619 | def _og_search_title(self, html, **kargs): | |
620 | return self._og_search_property('title', html, **kargs) | |
621 | ||
8ffa13e0 | 622 | def _og_search_video_url(self, html, name='video url', secure=True, **kargs): |
a3681973 PH |
623 | regexes = self._og_regexes('video') + self._og_regexes('video:url') |
624 | if secure: | |
625 | regexes = self._og_regexes('video:secure_url') + regexes | |
8ffa13e0 | 626 | return self._html_search_regex(regexes, html, name, **kargs) |
46720279 | 627 | |
78338f71 JMF |
628 | def _og_search_url(self, html, **kargs): |
629 | return self._og_search_property('url', html, **kargs) | |
630 | ||
40c696e5 | 631 | def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs): |
59040888 PH |
632 | if display_name is None: |
633 | display_name = name | |
634 | return self._html_search_regex( | |
6c6f1408 | 635 | r'''(?isx)<meta |
711ede6e | 636 | (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1) |
bec22481 | 637 | [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name), |
711ede6e | 638 | html, display_name, fatal=fatal, group='content', **kwargs) |
59040888 PH |
639 | |
640 | def _dc_search_uploader(self, html): | |
641 | return self._html_search_meta('dc.creator', html, 'uploader') | |
642 | ||
8dbe9899 PH |
643 | def _rta_search(self, html): |
644 | # See http://www.rtalabel.org/index.php?content=howtofaq#single | |
645 | if re.search(r'(?ix)<meta\s+name="rating"\s+' | |
646 | r' content="RTA-5042-1996-1400-1577-RTA"', | |
647 | html): | |
648 | return 18 | |
649 | return 0 | |
650 | ||
59040888 PH |
651 | def _media_rating_search(self, html): |
652 | # See http://www.tjg-designs.com/WP/metadata-code-examples-adding-metadata-to-your-web-pages/ | |
653 | rating = self._html_search_meta('rating', html) | |
654 | ||
655 | if not rating: | |
656 | return None | |
657 | ||
658 | RATING_TABLE = { | |
659 | 'safe for kids': 0, | |
660 | 'general': 8, | |
661 | '14 years': 14, | |
662 | 'mature': 17, | |
663 | 'restricted': 19, | |
664 | } | |
665 | return RATING_TABLE.get(rating.lower(), None) | |
666 | ||
69319969 NJ |
667 | def _family_friendly_search(self, html): |
668 | # See http://schema.org/VideoObj | |
669 | family_friendly = self._html_search_meta('isFamilyFriendly', html) | |
670 | ||
671 | if not family_friendly: | |
672 | return None | |
673 | ||
674 | RATING_TABLE = { | |
675 | '1': 0, | |
676 | 'true': 0, | |
677 | '0': 18, | |
678 | 'false': 18, | |
679 | } | |
680 | return RATING_TABLE.get(family_friendly.lower(), None) | |
681 | ||
0c708f11 JMF |
682 | def _twitter_search_player(self, html): |
683 | return self._html_search_meta('twitter:player', html, | |
9e1a5b84 | 684 | 'twitter card player') |
0c708f11 | 685 | |
4bcc7bd1 | 686 | def _sort_formats(self, formats): |
7e8caf30 | 687 | if not formats: |
f1a9d64e | 688 | raise ExtractorError('No video formats found') |
7e8caf30 | 689 | |
4bcc7bd1 | 690 | def _formats_key(f): |
e6812ac9 PH |
691 | # TODO remove the following workaround |
692 | from ..utils import determine_ext | |
693 | if not f.get('ext') and 'url' in f: | |
694 | f['ext'] = determine_ext(f['url']) | |
695 | ||
4bcc7bd1 PH |
696 | preference = f.get('preference') |
697 | if preference is None: | |
c7deaa4c PH |
698 | proto = f.get('protocol') |
699 | if proto is None: | |
700 | proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme | |
701 | ||
702 | preference = 0 if proto in ['http', 'https'] else -0.1 | |
4bcc7bd1 PH |
703 | if f.get('ext') in ['f4f', 'f4m']: # Not yet supported |
704 | preference -= 0.5 | |
705 | ||
706 | if f.get('vcodec') == 'none': # audio only | |
707 | if self._downloader.params.get('prefer_free_formats'): | |
f1a9d64e | 708 | ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus'] |
4bcc7bd1 | 709 | else: |
f1a9d64e | 710 | ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a'] |
4bcc7bd1 PH |
711 | ext_preference = 0 |
712 | try: | |
713 | audio_ext_preference = ORDER.index(f['ext']) | |
714 | except ValueError: | |
715 | audio_ext_preference = -1 | |
716 | else: | |
717 | if self._downloader.params.get('prefer_free_formats'): | |
f1a9d64e | 718 | ORDER = ['flv', 'mp4', 'webm'] |
4bcc7bd1 | 719 | else: |
f1a9d64e | 720 | ORDER = ['webm', 'flv', 'mp4'] |
4bcc7bd1 PH |
721 | try: |
722 | ext_preference = ORDER.index(f['ext']) | |
723 | except ValueError: | |
724 | ext_preference = -1 | |
725 | audio_ext_preference = 0 | |
726 | ||
727 | return ( | |
728 | preference, | |
aff2f4f4 | 729 | f.get('language_preference') if f.get('language_preference') is not None else -1, |
5d73273f | 730 | f.get('quality') if f.get('quality') is not None else -1, |
9933b574 | 731 | f.get('tbr') if f.get('tbr') is not None else -1, |
4bcc7bd1 | 732 | f.get('vbr') if f.get('vbr') is not None else -1, |
1a6373ef PH |
733 | f.get('height') if f.get('height') is not None else -1, |
734 | f.get('width') if f.get('width') is not None else -1, | |
1e1896f2 | 735 | ext_preference, |
4bcc7bd1 PH |
736 | f.get('abr') if f.get('abr') is not None else -1, |
737 | audio_ext_preference, | |
2c8e03d9 | 738 | f.get('fps') if f.get('fps') is not None else -1, |
4bcc7bd1 | 739 | f.get('filesize') if f.get('filesize') is not None else -1, |
9732d77e | 740 | f.get('filesize_approx') if f.get('filesize_approx') is not None else -1, |
c64ed2a3 | 741 | f.get('source_preference') if f.get('source_preference') is not None else -1, |
4bcc7bd1 PH |
742 | f.get('format_id'), |
743 | ) | |
744 | formats.sort(key=_formats_key) | |
59040888 | 745 | |
96a53167 S |
746 | def _check_formats(self, formats, video_id): |
747 | if formats: | |
748 | formats[:] = filter( | |
749 | lambda f: self._is_valid_url( | |
750 | f['url'], video_id, | |
751 | item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'), | |
752 | formats) | |
753 | ||
754 | def _is_valid_url(self, url, video_id, item='video'): | |
755 | try: | |
756 | self._request_webpage( | |
757 | HEADRequest(url), video_id, | |
758 | 'Checking %s URL' % item) | |
759 | return True | |
760 | except ExtractorError as e: | |
761 | if isinstance(e.cause, compat_HTTPError): | |
762 | self.report_warning( | |
763 | '%s URL is invalid, skipping' % item, video_id) | |
764 | return False | |
765 | raise | |
766 | ||
20991253 | 767 | def http_scheme(self): |
1ede5b24 | 768 | """ Either "http:" or "https:", depending on the user's preferences """ |
20991253 PH |
769 | return ( |
770 | 'http:' | |
771 | if self._downloader.params.get('prefer_insecure', False) | |
772 | else 'https:') | |
773 | ||
57c7411f PH |
774 | def _proto_relative_url(self, url, scheme=None): |
775 | if url is None: | |
776 | return url | |
777 | if url.startswith('//'): | |
778 | if scheme is None: | |
779 | scheme = self.http_scheme() | |
780 | return scheme + url | |
781 | else: | |
782 | return url | |
783 | ||
4094b6e3 PH |
784 | def _sleep(self, timeout, video_id, msg_template=None): |
785 | if msg_template is None: | |
f1a9d64e | 786 | msg_template = '%(video_id)s: Waiting for %(timeout)s seconds' |
4094b6e3 PH |
787 | msg = msg_template % {'video_id': video_id, 'timeout': timeout} |
788 | self.to_screen(msg) | |
789 | time.sleep(timeout) | |
790 | ||
60ca389c | 791 | def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None): |
f036a632 JMF |
792 | manifest = self._download_xml( |
793 | manifest_url, video_id, 'Downloading f4m manifest', | |
794 | 'Unable to download f4m manifest') | |
31bb8d3f JMF |
795 | |
796 | formats = [] | |
7a47d07c | 797 | manifest_version = '1.0' |
b2527359 | 798 | media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') |
34e48bed | 799 | if not media_nodes: |
7a47d07c | 800 | manifest_version = '2.0' |
34e48bed | 801 | media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') |
b2527359 | 802 | for i, media_el in enumerate(media_nodes): |
7a47d07c | 803 | if manifest_version == '2.0': |
3900eec2 S |
804 | manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/' |
805 | + (media_el.attrib.get('href') or media_el.attrib.get('url'))) | |
b2527359 | 806 | tbr = int_or_none(media_el.attrib.get('bitrate')) |
31bb8d3f | 807 | formats.append({ |
60ca389c | 808 | 'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])), |
31bb8d3f JMF |
809 | 'url': manifest_url, |
810 | 'ext': 'flv', | |
b2527359 | 811 | 'tbr': tbr, |
31bb8d3f JMF |
812 | 'width': int_or_none(media_el.attrib.get('width')), |
813 | 'height': int_or_none(media_el.attrib.get('height')), | |
60ca389c | 814 | 'preference': preference, |
31bb8d3f JMF |
815 | }) |
816 | self._sort_formats(formats) | |
817 | ||
818 | return formats | |
819 | ||
f0b5d6af | 820 | def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, |
60ca389c S |
821 | entry_protocol='m3u8', preference=None, |
822 | m3u8_id=None): | |
f0b5d6af | 823 | |
704df56d | 824 | formats = [{ |
60ca389c | 825 | 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])), |
704df56d PH |
826 | 'url': m3u8_url, |
827 | 'ext': ext, | |
828 | 'protocol': 'm3u8', | |
829 | 'preference': -1, | |
830 | 'resolution': 'multiple', | |
831 | 'format_note': 'Quality selection URL', | |
832 | }] | |
833 | ||
f0b5d6af PH |
834 | format_url = lambda u: ( |
835 | u | |
836 | if re.match(r'^https?://', u) | |
837 | else compat_urlparse.urljoin(m3u8_url, u)) | |
838 | ||
81515ad9 PH |
839 | m3u8_doc = self._download_webpage( |
840 | m3u8_url, video_id, | |
841 | note='Downloading m3u8 information', | |
842 | errnote='Failed to download m3u8 information') | |
704df56d PH |
843 | last_info = None |
844 | kv_rex = re.compile( | |
845 | r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)') | |
846 | for line in m3u8_doc.splitlines(): | |
847 | if line.startswith('#EXT-X-STREAM-INF:'): | |
848 | last_info = {} | |
849 | for m in kv_rex.finditer(line): | |
850 | v = m.group('val') | |
851 | if v.startswith('"'): | |
852 | v = v[1:-1] | |
853 | last_info[m.group('key')] = v | |
854 | elif line.startswith('#') or not line.strip(): | |
855 | continue | |
856 | else: | |
daebaab6 | 857 | if last_info is None: |
f0b5d6af | 858 | formats.append({'url': format_url(line)}) |
3524cc25 | 859 | continue |
704df56d | 860 | tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000) |
704df56d | 861 | f = { |
60ca389c | 862 | 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])), |
f0b5d6af | 863 | 'url': format_url(line.strip()), |
704df56d PH |
864 | 'tbr': tbr, |
865 | 'ext': ext, | |
f0b5d6af PH |
866 | 'protocol': entry_protocol, |
867 | 'preference': preference, | |
704df56d PH |
868 | } |
869 | codecs = last_info.get('CODECS') | |
870 | if codecs: | |
9ebf22b7 S |
871 | # TODO: looks like video codec is not always necessarily goes first |
872 | va_codecs = codecs.split(',') | |
873 | if va_codecs[0]: | |
874 | f['vcodec'] = va_codecs[0].partition('.')[0] | |
875 | if len(va_codecs) > 1 and va_codecs[1]: | |
876 | f['acodec'] = va_codecs[1].partition('.')[0] | |
704df56d PH |
877 | resolution = last_info.get('RESOLUTION') |
878 | if resolution: | |
879 | width_str, height_str = resolution.split('x') | |
880 | f['width'] = int(width_str) | |
881 | f['height'] = int(height_str) | |
882 | formats.append(f) | |
883 | last_info = {} | |
884 | self._sort_formats(formats) | |
885 | return formats | |
886 | ||
e89a2aab | 887 | # TODO: improve extraction |
995029a1 | 888 | def _extract_smil_formats(self, smil_url, video_id, fatal=True): |
e89a2aab S |
889 | smil = self._download_xml( |
890 | smil_url, video_id, 'Downloading SMIL file', | |
995029a1 PH |
891 | 'Unable to download SMIL file', fatal=fatal) |
892 | if smil is False: | |
893 | assert not fatal | |
894 | return [] | |
e89a2aab S |
895 | |
896 | base = smil.find('./head/meta').get('base') | |
897 | ||
898 | formats = [] | |
899 | rtmp_count = 0 | |
900 | for video in smil.findall('./body/switch/video'): | |
901 | src = video.get('src') | |
902 | if not src: | |
903 | continue | |
904 | bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) | |
905 | width = int_or_none(video.get('width')) | |
906 | height = int_or_none(video.get('height')) | |
907 | proto = video.get('proto') | |
908 | if not proto: | |
909 | if base: | |
910 | if base.startswith('rtmp'): | |
911 | proto = 'rtmp' | |
912 | elif base.startswith('http'): | |
913 | proto = 'http' | |
914 | ext = video.get('ext') | |
915 | if proto == 'm3u8': | |
916 | formats.extend(self._extract_m3u8_formats(src, video_id, ext)) | |
917 | elif proto == 'rtmp': | |
918 | rtmp_count += 1 | |
919 | streamer = video.get('streamer') or base | |
920 | formats.append({ | |
921 | 'url': streamer, | |
922 | 'play_path': src, | |
923 | 'ext': 'flv', | |
924 | 'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate), | |
925 | 'tbr': bitrate, | |
926 | 'width': width, | |
927 | 'height': height, | |
928 | }) | |
929 | self._sort_formats(formats) | |
930 | ||
931 | return formats | |
932 | ||
f4b1c7ad PH |
933 | def _live_title(self, name): |
934 | """ Generate the title for a live video """ | |
935 | now = datetime.datetime.now() | |
936 | now_str = now.strftime("%Y-%m-%d %H:%M") | |
937 | return name + ' ' + now_str | |
938 | ||
b14f3a4c PH |
939 | def _int(self, v, name, fatal=False, **kwargs): |
940 | res = int_or_none(v, **kwargs) | |
941 | if 'get_attr' in kwargs: | |
942 | print(getattr(v, kwargs['get_attr'])) | |
943 | if res is None: | |
944 | msg = 'Failed to extract %s: Could not parse value %r' % (name, v) | |
945 | if fatal: | |
946 | raise ExtractorError(msg) | |
947 | else: | |
948 | self._downloader.report_warning(msg) | |
949 | return res | |
950 | ||
951 | def _float(self, v, name, fatal=False, **kwargs): | |
952 | res = float_or_none(v, **kwargs) | |
953 | if res is None: | |
954 | msg = 'Failed to extract %s: Could not parse value %r' % (name, v) | |
955 | if fatal: | |
956 | raise ExtractorError(msg) | |
957 | else: | |
958 | self._downloader.report_warning(msg) | |
959 | return res | |
960 | ||
42939b61 | 961 | def _set_cookie(self, domain, name, value, expire_time=None): |
810fb84d PH |
962 | cookie = compat_cookiejar.Cookie( |
963 | 0, name, value, None, None, domain, None, | |
42939b61 JMF |
964 | None, '/', True, False, expire_time, '', None, None, None) |
965 | self._downloader.cookiejar.set_cookie(cookie) | |
966 | ||
05900629 PH |
967 | def get_testcases(self, include_onlymatching=False): |
968 | t = getattr(self, '_TEST', None) | |
969 | if t: | |
970 | assert not hasattr(self, '_TESTS'), \ | |
971 | '%s has _TEST and _TESTS' % type(self).__name__ | |
972 | tests = [t] | |
973 | else: | |
974 | tests = getattr(self, '_TESTS', []) | |
975 | for t in tests: | |
976 | if not include_onlymatching and t.get('only_matching', False): | |
977 | continue | |
978 | t['name'] = type(self).__name__[:-len('IE')] | |
979 | yield t | |
980 | ||
981 | def is_suitable(self, age_limit): | |
982 | """ Test whether the extractor is generally suitable for the given | |
983 | age limit (i.e. pornographic sites are not, all others usually are) """ | |
984 | ||
985 | any_restricted = False | |
986 | for tc in self.get_testcases(include_onlymatching=False): | |
987 | if 'playlist' in tc: | |
988 | tc = tc['playlist'][0] | |
989 | is_restricted = age_restricted( | |
990 | tc.get('info_dict', {}).get('age_limit'), age_limit) | |
991 | if not is_restricted: | |
992 | return True | |
993 | any_restricted = any_restricted or is_restricted | |
994 | return not any_restricted | |
995 | ||
8dbe9899 | 996 | |
d6983cb4 PH |
997 | class SearchInfoExtractor(InfoExtractor): |
998 | """ | |
999 | Base class for paged search queries extractors. | |
1000 | They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query} | |
1001 | Instances should define _SEARCH_KEY and _MAX_RESULTS. | |
1002 | """ | |
1003 | ||
1004 | @classmethod | |
1005 | def _make_valid_url(cls): | |
1006 | return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY | |
1007 | ||
1008 | @classmethod | |
1009 | def suitable(cls, url): | |
1010 | return re.match(cls._make_valid_url(), url) is not None | |
1011 | ||
1012 | def _real_extract(self, query): | |
1013 | mobj = re.match(self._make_valid_url(), query) | |
1014 | if mobj is None: | |
f1a9d64e | 1015 | raise ExtractorError('Invalid search query "%s"' % query) |
d6983cb4 PH |
1016 | |
1017 | prefix = mobj.group('prefix') | |
1018 | query = mobj.group('query') | |
1019 | if prefix == '': | |
1020 | return self._get_n_results(query, 1) | |
1021 | elif prefix == 'all': | |
1022 | return self._get_n_results(query, self._MAX_RESULTS) | |
1023 | else: | |
1024 | n = int(prefix) | |
1025 | if n <= 0: | |
f1a9d64e | 1026 | raise ExtractorError('invalid download number %s for query "%s"' % (n, query)) |
d6983cb4 | 1027 | elif n > self._MAX_RESULTS: |
f1a9d64e | 1028 | self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n)) |
d6983cb4 PH |
1029 | n = self._MAX_RESULTS |
1030 | return self._get_n_results(query, n) | |
1031 | ||
1032 | def _get_n_results(self, query, n): | |
1033 | """Get a specified number of results for a query""" | |
416a5efc | 1034 | raise NotImplementedError("This method must be implemented by subclasses") |
0f818663 PH |
1035 | |
1036 | @property | |
1037 | def SEARCH_KEY(self): | |
1038 | return self._SEARCH_KEY |