mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
New IE: YouTube channels (closes #396)
This commit is contained in:
parent
10daa766a1
commit
902b2a0a45
2 changed files with 51 additions and 0 deletions
|
@ -1578,6 +1578,56 @@ def _real_extract(self, url):
|
||||||
return
|
return
|
||||||
|
|
||||||
|
|
||||||
|
class YoutubeChannelIE(InfoExtractor):
|
||||||
|
"""Information Extractor for YouTube channels."""
|
||||||
|
|
||||||
|
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
|
||||||
|
_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
|
||||||
|
_MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
|
||||||
|
IE_NAME = u'youtube:channel'
|
||||||
|
|
||||||
|
def report_download_page(self, channel_id, pagenum):
|
||||||
|
"""Report attempt to download channel page with given number."""
|
||||||
|
self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
# Extract channel id
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
|
||||||
|
return
|
||||||
|
|
||||||
|
# Download channel pages
|
||||||
|
channel_id = mobj.group(1)
|
||||||
|
video_ids = []
|
||||||
|
pagenum = 1
|
||||||
|
|
||||||
|
while True:
|
||||||
|
self.report_download_page(channel_id, pagenum)
|
||||||
|
url = self._TEMPLATE_URL % (channel_id, pagenum)
|
||||||
|
request = urllib2.Request(url)
|
||||||
|
try:
|
||||||
|
page = urllib2.urlopen(request).read()
|
||||||
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
|
||||||
|
return
|
||||||
|
|
||||||
|
# Extract video identifiers
|
||||||
|
ids_in_page = []
|
||||||
|
for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
|
||||||
|
if mobj.group(1) not in ids_in_page:
|
||||||
|
ids_in_page.append(mobj.group(1))
|
||||||
|
video_ids.extend(ids_in_page)
|
||||||
|
|
||||||
|
if re.search(self._MORE_PAGES_INDICATOR, page) is None:
|
||||||
|
break
|
||||||
|
pagenum = pagenum + 1
|
||||||
|
|
||||||
|
for id in video_ids:
|
||||||
|
self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
|
||||||
|
return
|
||||||
|
|
||||||
|
|
||||||
class YoutubeUserIE(InfoExtractor):
|
class YoutubeUserIE(InfoExtractor):
|
||||||
"""Information Extractor for YouTube users."""
|
"""Information Extractor for YouTube users."""
|
||||||
|
|
||||||
|
|
|
@ -328,6 +328,7 @@ def gen_extractors():
|
||||||
"""
|
"""
|
||||||
return [
|
return [
|
||||||
YoutubePlaylistIE(),
|
YoutubePlaylistIE(),
|
||||||
|
YoutubeChannelIE(),
|
||||||
YoutubeUserIE(),
|
YoutubeUserIE(),
|
||||||
YoutubeSearchIE(),
|
YoutubeSearchIE(),
|
||||||
YoutubeIE(),
|
YoutubeIE(),
|
||||||
|
|
Loading…
Reference in a new issue