1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
|
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
class VeohIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/v(?P<id>\d*)'
_TEST = {
'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
'file': '56314296.mp4',
'md5': '620e68e6a3cff80086df3348426c9ca3',
'info_dict': {
'title': 'Straight Backs Are Stronger',
'uploader': 'LUMOback',
'description': 'At LUMOback, we believe straight backs are stronger. The LUMOback Posture & Movement Sensor: It gently vibrates when you slouch, inspiring improved posture and mobility. Use the app to track your data and improve your posture over time. ',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
m_youtube = re.search(r'http://www\.youtube\.com/v/(.*?)(\&|")', webpage)
if m_youtube is not None:
youtube_id = m_youtube.group(1)
self.to_screen('%s: detected Youtube video.' % video_id)
return self.url_result(youtube_id, 'Youtube')
self.report_extraction(video_id)
info = self._search_regex(r'videoDetailsJSON = \'({.*?})\';', webpage, 'info')
info = json.loads(info)
video_url = info.get('fullPreviewHashHighPath') or info.get('fullPreviewHashLowPath')
return {
'id': info['videoId'],
'title': info['title'],
'url': video_url,
'uploader': info['username'],
'thumbnail': info.get('highResImage') or info.get('medResImage'),
'description': info['description'],
'view_count': info['views'],
}
|