[extractor/common] Improve _json_ld

This commit is contained in:
Sergey M․ 2017-06-30 22:19:06 +07:00
parent d4f8ce6e91
commit c69701c6ab
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -1002,17 +1002,17 @@ def extract_video_object(e):
item_type = e.get('@type') item_type = e.get('@type')
if expected_type is not None and expected_type != item_type: if expected_type is not None and expected_type != item_type:
return info return info
if item_type == 'TVEpisode': if item_type in ('TVEpisode', 'Episode'):
info.update({ info.update({
'episode': unescapeHTML(e.get('name')), 'episode': unescapeHTML(e.get('name')),
'episode_number': int_or_none(e.get('episodeNumber')), 'episode_number': int_or_none(e.get('episodeNumber')),
'description': unescapeHTML(e.get('description')), 'description': unescapeHTML(e.get('description')),
}) })
part_of_season = e.get('partOfSeason') part_of_season = e.get('partOfSeason')
if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason': if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'):
info['season_number'] = int_or_none(part_of_season.get('seasonNumber')) info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries') part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries': if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'):
info['series'] = unescapeHTML(part_of_series.get('name')) info['series'] = unescapeHTML(part_of_series.get('name'))
elif item_type == 'Article': elif item_type == 'Article':
info.update({ info.update({
@ -1022,7 +1022,7 @@ def extract_video_object(e):
}) })
elif item_type == 'VideoObject': elif item_type == 'VideoObject':
extract_video_object(e) extract_video_object(e)
elif item_type == 'WebPage': continue
video = e.get('video') video = e.get('video')
if isinstance(video, dict) and video.get('@type') == 'VideoObject': if isinstance(video, dict) and video.get('@type') == 'VideoObject':
extract_video_object(video) extract_video_object(video)