[Teamcoco] Move into own file

This commit is contained in:
Philipp Hagemeister 2013-06-23 22:31:50 +02:00
parent 1ac4004f3a
commit cd8b830292
2 changed files with 47 additions and 38 deletions

View file

@ -57,6 +57,7 @@
from .extractor.spiegel import SpiegelIE from .extractor.spiegel import SpiegelIE
from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.stanfordoc import StanfordOpenClassroomIE
from .extractor.steam import SteamIE from .extractor.steam import SteamIE
from .extractor.teamcoco import TeamcocoIE
from .extractor.ted import TEDIE from .extractor.ted import TEDIE
from .extractor.tumblr import TumblrIE from .extractor.tumblr import TumblrIE
from .extractor.ustream import UstreamIE from .extractor.ustream import UstreamIE
@ -111,44 +112,6 @@
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
url_title = mobj.group('url_title')
webpage = self._download_webpage(url, url_title)
video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
webpage, u'video id')
self.report_extraction(video_id)
video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
webpage, u'title')
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
webpage, u'thumbnail', fatal=False)
video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
webpage, u'description', fatal=False)
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
data, u'video URL')
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
'description': video_description,
}]
class XHamsterIE(InfoExtractor): class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster""" """Information Extractor for xHamster"""

View file

@ -0,0 +1,46 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
url_title = mobj.group('url_title')
webpage = self._download_webpage(url, url_title)
video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
webpage, u'video id')
self.report_extraction(video_id)
video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
webpage, u'title')
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
webpage, u'thumbnail', fatal=False)
video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
webpage, u'description', fatal=False)
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
data, u'video URL')
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
'description': video_description,
}]