mirror of
https://github.com/l1ving/youtube-dl
synced 2024-12-24 01:03:07 +08:00
70 lines
2.5 KiB
Python
70 lines
2.5 KiB
Python
# encoding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_str
|
|
from ..utils import (
|
|
int_or_none,
|
|
parse_duration,
|
|
parse_iso8601,
|
|
)
|
|
|
|
|
|
class ComCarCoffIE(InfoExtractor):
|
|
_VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
|
|
_TESTS = [{
|
|
'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
|
|
'info_dict': {
|
|
'id': '2494164',
|
|
'ext': 'mp4',
|
|
'upload_date': '20141127',
|
|
'timestamp': 1417107600,
|
|
'duration': 1232,
|
|
'title': 'Happy Thanksgiving Miranda',
|
|
'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
|
|
},
|
|
'params': {
|
|
'skip_download': 'requires ffmpeg',
|
|
}
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
display_id = self._match_id(url)
|
|
if not display_id:
|
|
display_id = 'comediansincarsgettingcoffee.com'
|
|
webpage = self._download_webpage(url, display_id)
|
|
|
|
full_data = self._parse_json(
|
|
self._search_regex(
|
|
r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'),
|
|
display_id)['videoData']
|
|
|
|
display_id = full_data['activeVideo']['video']
|
|
video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id]
|
|
video_id = compat_str(video_data['mediaId'])
|
|
thumbnails = [{
|
|
'url': video_data['images']['thumb'],
|
|
}, {
|
|
'url': video_data['images']['poster'],
|
|
}]
|
|
|
|
timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601(
|
|
video_data.get('pubDate'))
|
|
duration = int_or_none(video_data.get('durationSeconds')) or parse_duration(
|
|
video_data.get('duration'))
|
|
|
|
return {
|
|
'_type': 'url_transparent',
|
|
'url': 'crackle:%s' % video_id,
|
|
'id': video_id,
|
|
'display_id': display_id,
|
|
'title': video_data['title'],
|
|
'description': video_data.get('description'),
|
|
'timestamp': timestamp,
|
|
'duration': duration,
|
|
'thumbnails': thumbnails,
|
|
'season_number': int_or_none(video_data.get('season')),
|
|
'episode_number': int_or_none(video_data.get('episode')),
|
|
'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
|
|
}
|