X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9bb07a5ee663304e100edc65967d5fc4a521bcd0..0e3c5183a16fb2d7b1ffb838220cc72b7578234e:/youtube_dl/extractor/common.py diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 8597866..a61753b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -15,7 +15,7 @@ import time import math from ..compat import ( - compat_cookiejar, + compat_cookiejar_Cookie, compat_cookies, compat_etree_Element, compat_etree_fromstring, @@ -1182,16 +1182,33 @@ class InfoExtractor(object): 'twitter card player') def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): - json_ld = self._search_regex( - JSON_LD_RE, html, 'JSON-LD', group='json_ld', **kwargs) + json_ld_list = list(re.finditer(JSON_LD_RE, html)) default = kwargs.get('default', NO_DEFAULT) - if not json_ld: - return default if default is not NO_DEFAULT else {} # JSON-LD may be malformed and thus `fatal` should be respected. # At the same time `default` may be passed that assumes `fatal=False` # for _search_regex. Let's simulate the same behavior here as well. fatal = kwargs.get('fatal', True) if default == NO_DEFAULT else False - return self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type) + json_ld = [] + for mobj in json_ld_list: + json_ld_item = self._parse_json( + mobj.group('json_ld'), video_id, fatal=fatal) + if not json_ld_item: + continue + if isinstance(json_ld_item, dict): + json_ld.append(json_ld_item) + elif isinstance(json_ld_item, (list, tuple)): + json_ld.extend(json_ld_item) + if json_ld: + json_ld = self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type) + if json_ld: + return json_ld + if default is not NO_DEFAULT: + return default + elif fatal: + raise RegexNotFoundError('Unable to extract JSON-LD') + else: + self._downloader.report_warning('unable to extract JSON-LD %s' % bug_reports_message()) + return {} def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None): if isinstance(json_ld, compat_str): @@ -1256,10 +1273,10 @@ class InfoExtractor(object): extract_interaction_statistic(e) for e in json_ld: - if isinstance(e.get('@context'), compat_str) and re.match(r'^https?://schema.org/?$', e.get('@context')): + if '@context' in e: item_type = e.get('@type') if expected_type is not None and expected_type != item_type: - return info + continue if item_type in ('TVEpisode', 'Episode'): episode_name = unescapeHTML(e.get('name')) info.update({ @@ -1293,11 +1310,17 @@ class InfoExtractor(object): }) elif item_type == 'VideoObject': extract_video_object(e) - continue + if expected_type is None: + continue + else: + break video = e.get('video') if isinstance(video, dict) and video.get('@type') == 'VideoObject': extract_video_object(video) - break + if expected_type is None: + continue + else: + break return dict((k, v) for k, v in info.items() if v is not None) @staticmethod @@ -1424,12 +1447,10 @@ class InfoExtractor(object): try: self._request_webpage(url, video_id, 'Checking %s URL' % item, headers=headers) return True - except ExtractorError as e: - if isinstance(e.cause, compat_urllib_error.URLError): - self.to_screen( - '%s: %s URL is invalid, skipping' % (video_id, item)) - return False - raise + except ExtractorError: + self.to_screen( + '%s: %s URL is invalid, skipping' % (video_id, item)) + return False def http_scheme(self): """ Either "http:" or "https:", depending on the user's preferences """ @@ -1457,14 +1478,14 @@ class InfoExtractor(object): def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), - fatal=True, m3u8_id=None): + fatal=True, m3u8_id=None, data=None, headers={}, query={}): manifest = self._download_xml( manifest_url, video_id, 'Downloading f4m manifest', 'Unable to download f4m manifest', # Some manifests may be malformed, e.g. prosiebensat1 generated manifests # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244) transform_source=transform_source, - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if manifest is False: return [] @@ -1588,12 +1609,13 @@ class InfoExtractor(object): def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, entry_protocol='m3u8', preference=None, m3u8_id=None, note=None, errnote=None, - fatal=True, live=False): + fatal=True, live=False, data=None, headers={}, + query={}): res = self._download_webpage_handle( m3u8_url, video_id, note=note or 'Downloading m3u8 information', errnote=errnote or 'Failed to download m3u8 information', - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] @@ -1767,6 +1789,19 @@ class InfoExtractor(object): # the same GROUP-ID f['acodec'] = 'none' formats.append(f) + + # for DailyMotion + progressive_uri = last_stream_inf.get('PROGRESSIVE-URI') + if progressive_uri: + http_f = f.copy() + del http_f['manifest_url'] + http_f.update({ + 'format_id': f['format_id'].replace('hls-', 'http-'), + 'protocol': 'http', + 'url': progressive_uri, + }) + formats.append(http_f) + last_stream_inf = {} return formats @@ -2011,12 +2046,12 @@ class InfoExtractor(object): }) return entries - def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}): + def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, data=None, headers={}, query={}): res = self._download_xml_handle( mpd_url, video_id, note=note or 'Downloading MPD manifest', errnote=errnote or 'Failed to download MPD manifest', - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] mpd_doc, urlh = res @@ -2319,15 +2354,17 @@ class InfoExtractor(object): self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) return formats - def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True): + def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}): res = self._download_xml_handle( ism_url, video_id, note=note or 'Downloading ISM manifest', errnote=errnote or 'Failed to download ISM manifest', - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] ism_doc, urlh = res + if ism_doc is None: + return [] return self._parse_ism_formats(ism_doc, urlh.geturl(), ism_id) @@ -2691,7 +2728,7 @@ class InfoExtractor(object): entry = { 'id': this_video_id, 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')), - 'description': video_data.get('description'), + 'description': clean_html(video_data.get('description')), 'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))), 'timestamp': int_or_none(video_data.get('pubdate')), 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), @@ -2806,7 +2843,7 @@ class InfoExtractor(object): def _set_cookie(self, domain, name, value, expire_time=None, port=None, path='/', secure=False, discard=False, rest={}, **kwargs): - cookie = compat_cookiejar.Cookie( + cookie = compat_cookiejar_Cookie( 0, name, value, port, port is not None, domain, True, domain.startswith('.'), path, True, secure, expire_time, discard, None, None, rest)