yt-dlp/youtube_dl/extractor/teamcoco.py

93 lines
3.2 KiB
Python
Raw Normal View History

2014-01-16 21:15:09 -05:00
from __future__ import unicode_literals
import base64
2013-06-23 16:31:50 -04:00
import re
from .common import InfoExtractor
from ..utils import qualities
2013-06-23 16:31:50 -04:00
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
_TESTS = [
2014-11-23 15:39:15 -05:00
{
'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
'md5': '3f7746aa0dc86de18df7539903d399ea',
'info_dict': {
'id': '80187',
'ext': 'mp4',
2014-11-23 15:39:15 -05:00
'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.',
'age_limit': 0,
2014-11-23 15:39:15 -05:00
}
}, {
'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
'info_dict': {
'id': '19705',
'ext': 'mp4',
'description': 'Louis C.K. got starstruck by George W. Bush, so what? Part one.',
'title': 'Louis C.K. Interview Pt. 1 11/3/11',
'age_limit': 0,
2014-11-23 15:39:15 -05:00
}
}
]
2015-02-11 08:47:19 -05:00
_VIDEO_ID_REGEXES = (
r'"eVar42"\s*:\s*(\d+)',
r'Ginger\.TeamCoco\.openInApp\("video",\s*"([^"]+)"',
r'"id_not"\s*:\s*(\d+)'
)
2013-06-23 16:31:50 -04:00
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 14:41:03 -05:00
video_id = mobj.group('video_id')
if not video_id:
video_id = self._html_search_regex(
2015-02-11 08:47:19 -05:00
self._VIDEO_ID_REGEXES, webpage, 'video id')
2013-06-23 16:31:50 -04:00
embed_url = 'http://teamcoco.com/embed/v/%s' % video_id
embed = self._download_webpage(
embed_url, video_id, 'Downloading embed page')
encoded_data = self._search_regex(
r'"preload"\s*:\s*"([^"]+)"', embed, 'encoded data')
data = self._parse_json(
base64.b64decode(encoded_data.encode('ascii')).decode('utf-8'), video_id)
2013-06-23 16:31:50 -04:00
formats = []
get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p'])
for filed in data['files']:
m_format = re.search(r'(\d+(k|p))\.mp4', filed['url'])
if m_format is not None:
format_id = m_format.group(1)
else:
format_id = filed['bitrate']
2014-01-16 21:22:02 -05:00
tbr = (
int(filed['bitrate'])
if filed['bitrate'].isdigit()
2014-01-16 21:22:02 -05:00
else None)
formats.append({
'url': filed['url'],
'ext': 'mp4',
2014-01-16 21:22:02 -05:00
'tbr': tbr,
'format_id': format_id,
'quality': get_quality(format_id),
})
2014-01-16 21:22:02 -05:00
self._sort_formats(formats)
2013-06-23 16:31:50 -04:00
return {
2014-01-16 21:15:09 -05:00
'id': video_id,
'display_id': display_id,
'formats': formats,
'title': data['title'],
'thumbnail': data.get('thumb', {}).get('href'),
'description': data.get('teaser'),
'age_limit': self._family_friendly_search(webpage),
}