mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-15 21:03:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

[yam] Fix title and uploader id

Browse source
This commit is contained in:
Yen Chi Hsuan 2015-05-09 17:36:07 +08:00
parent 32060c6d6b
commit 6d14d08e06
1 changed files with 22 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
youtube_dl/extractor/yam.py
View file

@ -9,6 +9,7 @@
float_or_none, float_or_none,
month_by_abbreviation, month_by_abbreviation,
ExtractorError, ExtractorError,
get_element_by_attribute,
) )
@ -23,6 +24,7 @@ class YamIE(InfoExtractor):
'id': '2283921', 'id': '2283921',
'ext': 'mp3', 'ext': 'mp3',
'title': '發現 - 趙薇 京華煙雲主題曲', 'title': '發現 - 趙薇 京華煙雲主題曲',
'description': '發現 - 趙薇 京華煙雲主題曲',
'uploader_id': 'princekt', 'uploader_id': 'princekt',
'upload_date': '20080807', 'upload_date': '20080807',
'duration': 313.0, 'duration': 313.0,
@ -55,6 +57,17 @@ class YamIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
}, },
'skip': 'invalid YouTube URL', 'skip': 'invalid YouTube URL',
}, {
'url': 'http://mymedia.yam.com/m/2373534',
'md5': '7ff74b91b7a817269d83796f8c5890b1',
'info_dict': {
'id': '2373534',
'ext': 'mp3',
'title': '林俊傑&蔡卓妍-小酒窩',
'description': 'md5:904003395a0fcce6cfb25028ff468420',
'upload_date': '20080928',
'uploader_id': 'onliner2',
}
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -75,15 +88,19 @@ def _real_extract(self, url):
if youtube_url: if youtube_url:
return self.url_result(youtube_url, 'Youtube') return self.url_result(youtube_url, 'Youtube')
title = self._html_search_regex(
r'<h1[^>]+class="heading"[^>]*>\s*(.+)\s*</h1>', page, 'title')
api_page = self._download_webpage( api_page = self._download_webpage(
'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id, 'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id,
note='Downloading API page') note='Downloading API page')
api_result_obj = compat_urlparse.parse_qs(api_page) api_result_obj = compat_urlparse.parse_qs(api_page)
info_table = get_element_by_attribute('class', 'info', page)
uploader_id = self._html_search_regex( uploader_id = self._html_search_regex(
r'<!-- 發表作者 -->：[\n ]+<a href="/([a-z]+)"', r'<!-- 發表作者 -->：[\n ]+<a href="/([a-z0-9]+)"',
page, 'uploader id', fatal=False) info_table, 'uploader id', fatal=False)
mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2}) ' + mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2})\s+' +
r'(?P<day>\d{1,2}), (?P<year>\d{4})', page) r'(?P<day>\d{1,2}), (?P<year>\d{4})', page)
if mobj: if mobj:
upload_date = '%s%02d%02d' % ( upload_date = '%s%02d%02d' % (
@ -97,7 +114,8 @@ def _real_extract(self, url):
return { return {
'id': video_id, 'id': video_id,
'url': api_result_obj['mp3file'][0], 'url': api_result_obj['mp3file'][0],
'title': self._html_search_meta('description', page), 'title': title,
'description': self._html_search_meta('description', page),
'duration': duration, 'duration': duration,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'upload_date': upload_date, 'upload_date': upload_date,