Browse Source

[QQMusic] Song extractor: Add lyrics as description

Note: Test fails on python 3 due to encoding issues
master
Yen Chi Hsuan 9 years ago
parent
commit
a685ae511a
1 changed files with 12 additions and 7 deletions
  1. 19
      youtube_dl/extractor/qqmusic.py

19
youtube_dl/extractor/qqmusic.py

@ -24,6 +24,7 @@ class QQMusicIE(InfoExtractor):
'title': '可惜没如果', 'title': '可惜没如果',
'upload_date': '20141227', 'upload_date': '20141227',
'creator': '林俊杰', 'creator': '林俊杰',
'description': 'md5:242c97c2847e0495583b7b13764f7106',
} }
}] }]
@ -47,10 +48,16 @@ class QQMusicIE(InfoExtractor):
publish_time = self._html_search_regex( publish_time = self._html_search_regex(
r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page, r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
'publish time').replace('-', '')
'publish time', default=None)
if publish_time:
publish_time = publish_time.replace('-', '')
singer = self._html_search_regex( singer = self._html_search_regex(
r"singer:\s*'([^']+)", detail_info_page, 'singer')
r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
lrc_content = self._html_search_regex(
r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
detail_info_page, 'LRC lyrics', default=None)
guid = self.m_r_get_ruin() guid = self.m_r_get_ruin()
@ -66,6 +73,7 @@ class QQMusicIE(InfoExtractor):
'title': song_name, 'title': song_name,
'upload_date': publish_time, 'upload_date': publish_time,
'creator': singer, 'creator': singer,
'description': lrc_content,
} }
@ -74,10 +82,6 @@ class QQPlaylistBaseIE(InfoExtractor):
def qq_static_url(category, mid): def qq_static_url(category, mid):
return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid) return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
@staticmethod
def qq_song_url(mid):
return 'http://y.qq.com/#type=song&mid=%s' % mid
@classmethod @classmethod
def get_entries_from_page(cls, page): def get_entries_from_page(cls, page):
entries = [] entries = []
@ -85,7 +89,8 @@ class QQPlaylistBaseIE(InfoExtractor):
for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page): for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
song_mid = unescapeHTML(item).split('|')[-5] song_mid = unescapeHTML(item).split('|')[-5]
entries.append(cls.url_result( entries.append(cls.url_result(
cls.qq_song_url(song_mid), 'QQMusic', song_mid))
'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
song_mid))
return entries return entries

Loading…
Cancel
Save