diff options
Diffstat (limited to 'youtube_dlc')
| -rw-r--r-- | youtube_dlc/extractor/bandcamp.py | 4 | ||||
| -rw-r--r-- | youtube_dlc/extractor/expressen.py | 7 | ||||
| -rw-r--r-- | youtube_dlc/extractor/iprima.py | 3 | ||||
| -rw-r--r-- | youtube_dlc/extractor/youtube.py | 12 |
4 files changed, 20 insertions, 6 deletions
diff --git a/youtube_dlc/extractor/bandcamp.py b/youtube_dlc/extractor/bandcamp.py index 2022e69f8..9dbafe86d 100644 --- a/youtube_dlc/extractor/bandcamp.py +++ b/youtube_dlc/extractor/bandcamp.py @@ -99,7 +99,6 @@ class BandcampIE(InfoExtractor): webpage, 'track info', default='{}') track_info = self._parse_json(trackinfo_block, title) - if track_info: file_ = track_info.get('file') if isinstance(file_, dict): @@ -115,7 +114,7 @@ class BandcampIE(InfoExtractor): 'acodec': ext, 'abr': int_or_none(abr_str), }) - track = track_info.get('title') + track_id = str_or_none(track_info.get('track_id') or track_info.get('id')) track_number = int_or_none(track_info.get('track_num')) duration = float_or_none(track_info.get('duration')) @@ -126,6 +125,7 @@ class BandcampIE(InfoExtractor): webpage, key, default=None, group='value') return data.replace(r'\"', '"').replace('\\\\', '\\') if data else data + track = extract('title') artist = extract('artist') album = extract('album_title') timestamp = unified_timestamp( diff --git a/youtube_dlc/extractor/expressen.py b/youtube_dlc/extractor/expressen.py index f79365038..dc8b855d2 100644 --- a/youtube_dlc/extractor/expressen.py +++ b/youtube_dlc/extractor/expressen.py @@ -15,7 +15,7 @@ from ..utils import ( class ExpressenIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// - (?:www\.)?expressen\.se/ + (?:www\.)?(?:expressen|di)\.se/ (?:(?:tvspelare/video|videoplayer/embed)/)? tv/(?:[^/]+/)* (?P<id>[^/?#&]+) @@ -42,13 +42,16 @@ class ExpressenIE(InfoExtractor): }, { 'url': 'https://www.expressen.se/videoplayer/embed/tv/ditv/ekonomistudion/experterna-har-ar-fragorna-som-avgor-valet/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di', 'only_matching': True, + }, { + 'url': 'https://www.di.se/videoplayer/embed/tv/ditv/borsmorgon/implantica-rusar-70--under-borspremiaren-hor-styrelsemedlemmen/?embed=true&external=true&autoplay=true&startVolume=0&partnerId=di', + 'only_matching': True, }] @staticmethod def _extract_urls(webpage): return [ mobj.group('url') for mobj in re.finditer( - r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?expressen\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1', + r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?(?:expressen|di)\.se/(?:tvspelare/video|videoplayer/embed)/tv/.+?)\1', webpage)] def _real_extract(self, url): diff --git a/youtube_dlc/extractor/iprima.py b/youtube_dlc/extractor/iprima.py index 53a550c11..648ae6741 100644 --- a/youtube_dlc/extractor/iprima.py +++ b/youtube_dlc/extractor/iprima.py @@ -86,7 +86,8 @@ class IPrimaIE(InfoExtractor): (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)', r'data-product="([^"]+)">', r'id=["\']player-(p\d+)"', - r'playerId\s*:\s*["\']player-(p\d+)'), + r'playerId\s*:\s*["\']player-(p\d+)', + r'\bvideos\s*=\s*["\'](p\d+)'), webpage, 'real id') playerpage = self._download_webpage( diff --git a/youtube_dlc/extractor/youtube.py b/youtube_dlc/extractor/youtube.py index 293d6069d..e68395583 100644 --- a/youtube_dlc/extractor/youtube.py +++ b/youtube_dlc/extractor/youtube.py @@ -39,6 +39,7 @@ from ..utils import ( mimetype2ext, orderedSet, parse_codecs, + parse_count, parse_duration, remove_quotes, remove_start, @@ -2455,7 +2456,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_count(count_name): return str_to_int(self._search_regex( - r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' + r'"accessibilityData":\{"label":"([\d,\w]+) %ss"\}' % re.escape(count_name), video_webpage, count_name, default=None)) @@ -2484,6 +2485,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_duration = parse_duration(self._html_search_meta( 'duration', video_webpage, 'video duration')) + # Get Subscriber Count of channel + subscriber_count = parse_count(self._search_regex( + r'"text":"([\d\.]+\w?) subscribers"', + video_webpage, + 'subscriber count', + default=None + )) + # annotations video_annotations = None if self._downloader.params.get('writeannotations', False): @@ -2621,6 +2630,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'album': album, 'release_date': release_date, 'release_year': release_year, + 'subscriber_count': subscriber_count, } |