yt-dlc/youtube_dl/extractor/teamcoco.py

72 lines
2.3 KiB
Python
Raw Normal View History

2014-01-17 03:15:09 +01:00
from __future__ import unicode_literals
2013-06-23 22:31:50 +02:00
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
2013-06-27 20:46:46 +02:00
_TEST = {
2014-01-17 03:15:09 +01:00
'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
'file': '19705.mp4',
'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
'info_dict': {
"description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
"title": "Louis C.K. Interview Pt. 1 11/3/11"
2013-06-27 20:46:46 +02:00
}
}
2013-06-23 22:31:50 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
2014-01-17 03:15:09 +01:00
raise ExtractorError('Invalid URL: %s' % url)
2013-06-23 22:31:50 +02:00
url_title = mobj.group('url_title')
webpage = self._download_webpage(url, url_title)
2014-01-17 03:15:09 +01:00
video_id = self._html_search_regex(
r'<article class="video" data-id="(\d+?)"',
webpage, 'video id')
2013-06-23 22:31:50 +02:00
self.report_extraction(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')
2013-06-23 22:31:50 +02:00
qualities = ['500k', '480p', '1000k', '720p', '1080p']
formats = []
for file in data.findall('files/file'):
if file.attrib.get('playmode') == 'all':
# it just duplicates one of the entries
break
file_url = file.text
m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
if m_format is not None:
format_id = m_format.group(1)
else:
format_id = file.attrib['bitrate']
formats.append({
'url': file_url,
'ext': 'mp4',
'format_id': format_id,
})
def sort_key(f):
try:
return qualities.index(f['format_id'])
except ValueError:
return -1
formats.sort(key=sort_key)
if not formats:
2014-01-17 03:15:09 +01:00
raise ExtractorError('Unable to extract video URL')
2013-06-23 22:31:50 +02:00
return {
2014-01-17 03:15:09 +01:00
'id': video_id,
'formats': formats,
2014-01-17 03:15:09 +01:00
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
}