PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-03 08:43:58 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

fix playlist download

Browse Source
This commit is contained in:
Chuntao Hong 2016-07-20 12:04:15 +08:00
parent 5295d1160c
commit b95b1a10ee
1 changed files with 13 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
src/you_get/extractors/youku.py
View File

@ -76,7 +76,7 @@ class Youku(VideoExtractor):
for x in xs: for x in xs:
if x not in mem: if x not in mem:
mem.add(x) mem.add(x)
yield(x) return mem
def get_vid_from_url(url): def get_vid_from_url(url):
"""Extracts video ID from URL. """Extracts video ID from URL.
@ -89,7 +89,7 @@ class Youku(VideoExtractor):
def get_playlist_id_from_url(url): def get_playlist_id_from_url(url):
"""Extracts playlist ID from URL. """Extracts playlist ID from URL.
""" """
return match1(url, r'youku\.com/playlist_show/id_([a-zA-Z0-9=]+)') return match1(url, r'youku\.com/albumlist/show\?id=([a-zA-Z0-9=]+)')
def download_playlist_by_url(self, url, **kwargs): def download_playlist_by_url(self, url, **kwargs):
self.url = url self.url = url
@ -97,16 +97,19 @@ class Youku(VideoExtractor):
try: try:
playlist_id = self.__class__.get_playlist_id_from_url(self.url) playlist_id = self.__class__.get_playlist_id_from_url(self.url)
assert playlist_id assert playlist_id
video_page = get_content('http://list.youku.com/albumlist/show?id=%s' % playlist_id)
video_page = get_content('http://www.youku.com/playlist_show/id_%s' % playlist_id)
videos = Youku.oset(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', video_page)) videos = Youku.oset(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', video_page))
# Parse multi-page playlists # Parse multi-page playlists
for extra_page_url in Youku.oset(re.findall('href="(http://www\.youku\.com/playlist_show/id_%s_[^?"]+)' % playlist_id, video_page)): last_page_url = re.findall(r'href="(/albumlist/show\?id=%s[^"]+)" title="末页"' % playlist_id, video_page)[0]
extra_page = get_content(extra_page_url) num_pages = int(re.findall(r'page=([0-9]+)\.htm', last_page_url)[0])
if (num_pages > 0):
# download one by one
for pn in range(1, num_pages + 1):
extra_page_url = re.sub(r'page=([0-9]+)\.htm', r'page=%s.htm' % pn, last_page_url)
extra_page = get_content('http://list.youku.com' + extra_page_url)
videos |= Youku.oset(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', extra_page)) videos |= Youku.oset(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', extra_page))
except Exception as e:
except: print(e)
# Show full list of episodes # Show full list of episodes
if match1(url, r'youku\.com/show_page/id_([a-zA-Z0-9=]+)'): if match1(url, r'youku\.com/show_page/id_([a-zA-Z0-9=]+)'):
ep_id = match1(url, r'youku\.com/show_page/id_([a-zA-Z0-9=]+)') ep_id = match1(url, r'youku\.com/show_page/id_([a-zA-Z0-9=]+)')