etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[crunchyroll] Extract season name

Browse source
This commit is contained in:
Starsam80 2017-03-11 21:18:10 -07:00 committed by Sergey M
parent 57b0ddb35f
commit 8c99623259
1 changed files with 21 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
youtube_dl/extractor/crunchyroll.py
View file

@ -177,6 +177,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'uploader': 'Kadokawa Pictures Inc.', 'uploader': 'Kadokawa Pictures Inc.',
'upload_date': '20170118', 'upload_date': '20170118',
'series': "KONOSUBA -God's blessing on this wonderful world!", 'series': "KONOSUBA -God's blessing on this wonderful world!",
'season': "KONOSUBA -God's blessing on this wonderful world! 2",
'season_number': 2, 'season_number': 2,
'episode': 'Give Me Deliverance from this Judicial Injustice!', 'episode': 'Give Me Deliverance from this Judicial Injustice!',
'episode_number': 1, 'episode_number': 1,
@ -222,6 +223,23 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# just test metadata extraction # just test metadata extraction
'skip_download': True, 'skip_download': True,
}, },
}, {
# A video with a vastly different season name compared to the series name
'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532',
'info_dict': {
'id': '590532',
'ext': 'mp4',
'title': 'Haiyoru! Nyaruani (ONA) Episode 1 – Test',
'description': 'Mahiro and Nyaruko talk about official certification.',
'uploader': 'TV TOKYO',
'upload_date': '20120305',
'series': 'Nyarko-san: Another Crawling Chaos',
'season': 'Haiyoru! Nyaruani (ONA)',
},
'params': {
# Just test metadata extraction
'skip_download': True,
},
}] }]
_FORMAT_IDS = { _FORMAT_IDS = {
@ -491,7 +509,8 @@ def _real_extract(self, url):
# webpage provide more accurate data than series_title from XML # webpage provide more accurate data than series_title from XML
series = self._html_search_regex( series = self._html_search_regex(
r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)', r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
webpage, 'series', default=xpath_text(metadata, 'series_title')) webpage, 'series', fatal=False)
season = xpath_text(metadata, 'series_title')
episode = xpath_text(metadata, 'episode_title') episode = xpath_text(metadata, 'episode_title')
episode_number = int_or_none(xpath_text(metadata, 'episode_number')) episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
@ -508,6 +527,7 @@ def _real_extract(self, url):
'uploader': video_uploader, 'uploader': video_uploader,
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'series': series, 'series': series,
'season': season,
'season_number': season_number, 'season_number': season_number,
'episode': episode, 'episode': episode,
'episode_number': episode_number, 'episode_number': episode_number,