|
|
@ -1,3 +1,5 @@
|
|
|
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
|
|
import re
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
from .common import InfoExtractor
|
|
|
@ -9,31 +11,31 @@ from ..utils import (
|
|
|
|
class TeamcocoIE(InfoExtractor):
|
|
|
|
class TeamcocoIE(InfoExtractor):
|
|
|
|
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
|
|
|
|
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
|
|
|
|
_TEST = {
|
|
|
|
_TEST = {
|
|
|
|
u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
|
|
|
|
'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
|
|
|
|
u'file': u'19705.mp4',
|
|
|
|
'file': '19705.mp4',
|
|
|
|
u'md5': u'cde9ba0fa3506f5f017ce11ead928f9a',
|
|
|
|
'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
|
|
|
|
u'info_dict': {
|
|
|
|
'info_dict': {
|
|
|
|
u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.",
|
|
|
|
"description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
|
|
|
|
u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
|
|
|
|
"title": "Louis C.K. Interview Pt. 1 11/3/11"
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
def _real_extract(self, url):
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
if mobj is None:
|
|
|
|
if mobj is None:
|
|
|
|
raise ExtractorError(u'Invalid URL: %s' % url)
|
|
|
|
raise ExtractorError('Invalid URL: %s' % url)
|
|
|
|
url_title = mobj.group('url_title')
|
|
|
|
url_title = mobj.group('url_title')
|
|
|
|
webpage = self._download_webpage(url, url_title)
|
|
|
|
webpage = self._download_webpage(url, url_title)
|
|
|
|
|
|
|
|
|
|
|
|
video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
|
|
|
|
video_id = self._html_search_regex(
|
|
|
|
webpage, u'video id')
|
|
|
|
r'<article class="video" data-id="(\d+?)"',
|
|
|
|
|
|
|
|
webpage, 'video id')
|
|
|
|
|
|
|
|
|
|
|
|
self.report_extraction(video_id)
|
|
|
|
self.report_extraction(video_id)
|
|
|
|
|
|
|
|
|
|
|
|
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
|
|
|
|
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
|
|
|
|
data = self._download_xml(data_url, video_id, 'Downloading data webpage')
|
|
|
|
data = self._download_xml(data_url, video_id, 'Downloading data webpage')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qualities = ['500k', '480p', '1000k', '720p', '1080p']
|
|
|
|
qualities = ['500k', '480p', '1000k', '720p', '1080p']
|
|
|
|
formats = []
|
|
|
|
formats = []
|
|
|
|
for file in data.findall('files/file'):
|
|
|
|
for file in data.findall('files/file'):
|
|
|
@ -58,7 +60,7 @@ class TeamcocoIE(InfoExtractor):
|
|
|
|
return -1
|
|
|
|
return -1
|
|
|
|
formats.sort(key=sort_key)
|
|
|
|
formats.sort(key=sort_key)
|
|
|
|
if not formats:
|
|
|
|
if not formats:
|
|
|
|
raise ExtractorError(u'Unable to extract video URL')
|
|
|
|
raise ExtractorError('Unable to extract video URL')
|
|
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
return {
|
|
|
|
'id': video_id,
|
|
|
|
'id': video_id,
|
|
|
|