Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/bambuser.py

   1 import re
   2 import json
   3 import itertools
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urllib_request,
   8 )
   9
  10
  11 class BambuserIE(InfoExtractor):
  12     IE_NAME = u'bambuser'
  13     _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
  14     _API_KEY = '005f64509e19a868399060af746a00aa'
  15
  16     _TEST = {
  17         u'url': u'http://bambuser.com/v/4050584',
  18         u'md5': u'fba8f7693e48fd4e8641b3fd5539a641',
  19         u'info_dict': {
  20             u'id': u'4050584',
  21             u'ext': u'flv',
  22             u'title': u'Education engineering days - lightning talks',
  23             u'duration': 3741,
  24             u'uploader': u'pixelversity',
  25             u'uploader_id': u'344706',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         info_url = ('http://player-c.api.bambuser.com/getVideo.json?'
  33             '&api_key=%s&vid=%s' % (self._API_KEY, video_id))
  34         info_json = self._download_webpage(info_url, video_id)
  35         info = json.loads(info_json)['result']
  36
  37         return {
  38             'id': video_id,
  39             'title': info['title'],
  40             'url': info['url'],
  41             'thumbnail': info.get('preview'),
  42             'duration': int(info['length']),
  43             'view_count': int(info['views_total']),
  44             'uploader': info['username'],
  45             'uploader_id': info['uid'],
  46         }
  47
  48
  49 class BambuserChannelIE(InfoExtractor):
  50     IE_NAME = u'bambuser:channel'
  51     _VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
  52     # The maximum number we can get with each request
  53     _STEP = 50
  54
  55     def _real_extract(self, url):
  56         mobj = re.match(self._VALID_URL, url)
  57         user = mobj.group('user')
  58         urls = []
  59         last_id = ''
  60         for i in itertools.count(1):
  61             req_url = ('http://bambuser.com/xhr-api/index.php?username={user}'
  62                 '&sort=created&access_mode=0%2C1%2C2&limit={count}'
  63                 '&method=broadcast&format=json&vid_older_than={last}'
  64                 ).format(user=user, count=self._STEP, last=last_id)
  65             req = compat_urllib_request.Request(req_url)
  66             # Without setting this header, we wouldn't get any result
  67             req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
  68             info_json = self._download_webpage(req, user,
  69                 u'Downloading page %d' % i)
  70             results = json.loads(info_json)['result']
  71             if len(results) == 0:
  72                 break
  73             last_id = results[-1]['vid']
  74             urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)
  75
  76         return {
  77             '_type': 'playlist',
  78             'title': user,
  79             'entries': urls,
  80         }