PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-03-13 03:17:44 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[youku] implement oset(xs), which removes duplicates from a list and keeps the original order

Browse Source
This commit is contained in:
Mort Yao 2015-12-15 04:36:00 +01:00
parent da4dcc9b85
commit facee031a8
1 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/you_get/extractors/youku.py
View File

@ -66,6 +66,14 @@ class Youku(VideoExtractor):
def parse_m3u8(m3u8): def parse_m3u8(m3u8):
return re.findall(r'(http://[^?]+)\?ts_start=0', m3u8) return re.findall(r'(http://[^?]+)\?ts_start=0', m3u8)
def oset(xs):
"""Turns a list into an ordered set. (removes duplicates)"""
mem = set()
for x in xs:
if x not in mem:
mem.add(x)
yield(x)
def get_vid_from_url(url): def get_vid_from_url(url):
"""Extracts video ID from URL. """Extracts video ID from URL.
""" """
@ -87,12 +95,12 @@ class Youku(VideoExtractor):
assert playlist_id assert playlist_id
video_page = get_content('http://www.youku.com/playlist_show/id_%s' % playlist_id) video_page = get_content('http://www.youku.com/playlist_show/id_%s' % playlist_id)
videos = set(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 set(re.findall('href="(http://www\.youku\.com/playlist_show/id_%s_[^?"]+)' % playlist_id, video_page)): for extra_page_url in Youku.oset(re.findall('href="(http://www\.youku\.com/playlist_show/id_%s_[^?"]+)' % playlist_id, video_page)):
extra_page = get_content(extra_page_url) extra_page = get_content(extra_page_url)
videos |= set(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', extra_page)) videos |= Youku.oset(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', extra_page))
except: except:
# Show full list of episodes # Show full list of episodes
@ -101,7 +109,7 @@ class Youku(VideoExtractor):
url = 'http://www.youku.com/show_episode/id_%s' % ep_id url = 'http://www.youku.com/show_episode/id_%s' % ep_id
video_page = get_content(url) video_page = get_content(url)
videos = set(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', video_page)) videos = Youku.oset(re.findall(r'href="(http://v\.youku\.com/[^?"]+)', video_page))
self.title = r1(r'<meta name="title" content="([^"]+)"', video_page) or \ self.title = r1(r'<meta name="title" content="([^"]+)"', video_page) or \
r1(r'<title>([^<]+)', video_page) r1(r'<title>([^<]+)', video_page)