1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-16 22:34:33 +01:00
youtube-dl/youtube_dl/extractor/teamcoco.py

85 lines
2.9 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
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
_TESTS = [
2014-11-23 21:39:15 +01:00
{
'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
'file': '80187.mp4',
'md5': '3f7746aa0dc86de18df7539903d399ea',
'info_dict': {
'title': 'Conan Becomes A Mary Kay Beauty Consultant',
'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
}
}, {
'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"
}
}
]
2013-06-23 22:31:50 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
2014-11-23 20:41:03 +01:00
video_id = mobj.group("video_id")
if not video_id:
video_id = self._html_search_regex(
2014-08-20 15:30:29 +02:00
r'data-node-id="(\d+?)"',
webpage, 'video id')
2013-06-23 22:31:50 +02:00
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
data = self._download_xml(
data_url, display_id, 'Downloading data webpage')
2013-06-23 22:31:50 +02:00
qualities = ['500k', '480p', '1000k', '720p', '1080p']
formats = []
2014-01-17 03:22:02 +01:00
for filed in data.findall('files/file'):
if filed.attrib.get('playmode') == 'all':
# it just duplicates one of the entries
break
2014-01-17 03:22:02 +01:00
file_url = filed.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:
2014-01-17 03:22:02 +01:00
format_id = filed.attrib['bitrate']
tbr = (
int(filed.attrib['bitrate'])
if filed.attrib['bitrate'].isdigit()
else None)
try:
quality = qualities.index(format_id)
except ValueError:
quality = -1
formats.append({
'url': file_url,
'ext': 'mp4',
2014-01-17 03:22:02 +01:00
'tbr': tbr,
'format_id': format_id,
2014-01-17 03:22:02 +01:00
'quality': quality,
})
2014-01-17 03:22:02 +01:00
self._sort_formats(formats)
2013-06-23 22:31:50 +02:00
return {
2014-01-17 03:15:09 +01:00
'id': video_id,
'display_id': display_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),
}