X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a070911bf98c751e4425008f1335cc57c86d30fc..d317bf370d3cbd2231f3d6b1970e0a86fddc4e5b:/youtube_dl/extractor/common.py diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 03f3f18..b9014fc 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -14,6 +14,7 @@ import xml.etree.ElementTree from ..compat import ( compat_cookiejar, + compat_HTTPError, compat_http_client, compat_urllib_error, compat_urllib_parse_urlparse, @@ -21,17 +22,20 @@ from ..compat import ( compat_str, ) from ..utils import ( + NO_DEFAULT, age_restricted, + bug_reports_message, clean_html, compiled_regex_type, + determine_ext, ExtractorError, + fix_xml_ampersands, float_or_none, int_or_none, RegexNotFoundError, sanitize_filename, unescapeHTML, ) -_NO_DEFAULT = object() class InfoExtractor(object): @@ -45,7 +49,7 @@ class InfoExtractor(object): information possibly downloading the video to the file system, among other possible outcomes. - The type field determines the the type of the result. + The type field determines the type of the result. By far the most common value (and the default if _type is missing) is "video", which indicates a single video. @@ -87,7 +91,8 @@ class InfoExtractor(object): * player_url SWF Player URL (used for rtmpdump). * protocol The protocol that will be used for the actual download, lower-case. - "http", "https", "rtsp", "rtmp", "m3u8" or so. + "http", "https", "rtsp", "rtmp", "rtmpe", + "m3u8", or "m3u8_native". * preference Order number of this format. If this field is present and not None, the formats get sorted by this field, regardless of all other values. @@ -108,15 +113,14 @@ class InfoExtractor(object): (quality takes higher priority) -1 for default (order by other properties), -2 or smaller for less than default. - * http_referer HTTP Referer header value to set. - * http_method HTTP method to use for the download. * http_headers A dictionary of additional HTTP headers to add to the request. - * http_post_data Additional data to send with a POST - request. * stretched_ratio If given and not 1, indicates that the - video's pixels are not square. - width : height ratio as float. + video's pixels are not square. + width : height ratio as float. + * no_resume The server does not support resuming the + (HTTP or RTMP) download. Boolean. + url: Final video URL. ext: Video filename extension. format: The video format, defaults to ext (used for --get-format) @@ -130,7 +134,9 @@ class InfoExtractor(object): something like "4234987", title "Dancing naked mole rats", and display_id "dancing-naked-mole-rats" thumbnails: A list of dictionaries, with the following entries: + * "id" (optional, string) - Thumbnail format ID * "url" + * "preference" (optional, int) - quality of the image * "width" (optional, int) * "height" (optional, int) * "resolution" (optional, string "{width}x{height"}, @@ -138,17 +144,25 @@ class InfoExtractor(object): thumbnail: Full URL to a video thumbnail image. description: Full video description. uploader: Full name of the video uploader. + creator: The main artist who created the video. timestamp: UNIX timestamp of the moment the video became available. upload_date: Video upload date (YYYYMMDD). If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. location: Physical location where the video was filmed. - subtitles: The subtitle file contents as a dictionary in the format - {language: subtitles}. + subtitles: The available subtitles as a dictionary in the format + {language: subformats}. "subformats" is a list sorted from + lower to higher preference, each element is a dictionary + with the "ext" entry and one of: + * "data": The subtitles file contents + * "url": A url pointing to the subtitles file + automatic_captions: Like 'subtitles', used by the YoutubeIE for + automatically generated captions duration: Length of the video in seconds, as an integer. view_count: How many users have watched the video on the platform. like_count: Number of positive ratings of the video dislike_count: Number of negative ratings of the video + average_rating: Average rating give by users, the scale used depends on the webpage comment_count: Number of comments on the video comments: A list of comments, each with one or more of the following properties (all but one of text or html optional): @@ -256,8 +270,15 @@ class InfoExtractor(object): def extract(self, url): """Extracts URL information and returns it in list of dicts.""" - self.initialize() - return self._real_extract(url) + try: + self.initialize() + return self._real_extract(url) + except ExtractorError: + raise + except compat_http_client.IncompleteRead as e: + raise ExtractorError('A network error has occured.', cause=e, expected=True) + except (KeyError, StopIteration) as e: + raise ExtractorError('An extractor error has occured.', cause=e) def set_downloader(self, downloader): """Sets the downloader for this IE.""" @@ -303,7 +324,7 @@ class InfoExtractor(object): self._downloader.report_warning(errmsg) return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): @@ -313,14 +334,11 @@ class InfoExtractor(object): if urlh is False: assert not fatal return False - content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal) + content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding) return (content, urlh) - def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None): - content_type = urlh.headers.get('Content-Type', '') - webpage_bytes = urlh.read() - if prefix is not None: - webpage_bytes = prefix + webpage_bytes + @staticmethod + def _guess_encoding_from_content(content_type, webpage_bytes): m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) if m: encoding = m.group(1) @@ -333,6 +351,16 @@ class InfoExtractor(object): encoding = 'utf-16' else: encoding = 'utf-8' + + return encoding + + def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None): + content_type = urlh.headers.get('Content-Type', '') + webpage_bytes = urlh.read() + if prefix is not None: + webpage_bytes = prefix + webpage_bytes + if not encoding: + encoding = self._guess_encoding_from_content(content_type, webpage_bytes) if self._downloader.params.get('dump_intermediate_pages', False): try: url = url_or_request.get_full_url() @@ -376,16 +404,26 @@ class InfoExtractor(object): if blocked_iframe: msg += ' Visit %s for more details' % blocked_iframe raise ExtractorError(msg, expected=True) + if '
(.*?)
', + content, 'block message', default=None) + if block_msg: + msg += ' (Message: "%s")' % block_msg.replace('\n', ' ') + raise ExtractorError(msg, expected=True) return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): """ Returns the data of the page as a string """ success = False try_count = 0 while success is False: try: - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -400,10 +438,10 @@ class InfoExtractor(object): def _download_xml(self, url_or_request, video_id, note='Downloading XML', errnote='Unable to download XML', - transform_source=None, fatal=True): + transform_source=None, fatal=True, encoding=None): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal) + url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding) if xml_string is False: return xml_string if transform_source: @@ -414,9 +452,10 @@ class InfoExtractor(object): note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True): + fatal=True, encoding=None): json_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal) + url_or_request, video_id, note, errnote, fatal=fatal, + encoding=encoding) if (not fatal) and json_string is False: return None return self._parse_json( @@ -461,7 +500,7 @@ class InfoExtractor(object): # Methods for following #608 @staticmethod - def url_result(url, ie=None, video_id=None): + def url_result(url, ie=None, video_id=None, video_title=None): """Returns a url that points to a page that should be processed""" # TODO: ie should be the class used for getting the info video_info = {'_type': 'url', @@ -469,6 +508,8 @@ class InfoExtractor(object): 'ie_key': ie} if video_id is not None: video_info['id'] = video_id + if video_title is not None: + video_info['title'] = video_title return video_info @staticmethod @@ -484,7 +525,7 @@ class InfoExtractor(object): video_info['description'] = playlist_description return video_info - def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): + def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None): """ Perform a regex search on the given string, using a single or a list of patterns returning the first matching group. @@ -499,7 +540,7 @@ class InfoExtractor(object): if mobj: break - if os.name != 'nt' and sys.stderr.isatty(): + if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty(): _name = '\033[0;34m%s\033[0m' % name else: _name = name @@ -510,16 +551,15 @@ class InfoExtractor(object): return next(g for g in mobj.groups() if g is not None) else: return mobj.group(group) - elif default is not _NO_DEFAULT: + elif default is not NO_DEFAULT: return default elif fatal: raise RegexNotFoundError('Unable to extract %s' % _name) else: - self._downloader.report_warning('unable to extract %s; ' - 'please report this issue on http://yt-dl.org/bug' % _name) + self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message()) return None - def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None): + def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None): """ Like _search_regex, but strips HTML tags and unescapes entities. """ @@ -531,7 +571,7 @@ class InfoExtractor(object): def _get_login_info(self): """ - Get the the login info as (username, password) + Get the login info as (username, password) It will look in the netrc file using the _NETRC_MACHINE value If there's no info available, return (None, None) """ @@ -648,11 +688,45 @@ class InfoExtractor(object): } return RATING_TABLE.get(rating.lower(), None) + def _family_friendly_search(self, html): + # See http://schema.org/VideoObject + family_friendly = self._html_search_meta('isFamilyFriendly', html) + + if not family_friendly: + return None + + RATING_TABLE = { + '1': 0, + 'true': 0, + '0': 18, + 'false': 18, + } + return RATING_TABLE.get(family_friendly.lower(), None) + def _twitter_search_player(self, html): return self._html_search_meta('twitter:player', html, 'twitter card player') - def _sort_formats(self, formats): + @staticmethod + def _hidden_inputs(html): + return dict([ + (input.group('name'), input.group('value')) for input in re.finditer( + r'''(?x) + ["\'])hidden(?P=q_hidden)\s+ + name=(?P