[breakcom] Modernize

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-10 20:48:46 +01:00
parent fde56d2f17
commit ebfe352b62

View file

@ -1,18 +1,20 @@
from __future__ import unicode_literals
import re import re
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import determine_ext
class BreakIE(InfoExtractor): class BreakIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)' _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
_TEST = { _TEST = {
u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056', 'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
u'file': u'2468056.mp4', 'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b', 'info_dict': {
u'info_dict': { 'id': '2468056',
u"title": u"When Girls Act Like D-Bags" 'ext': 'mp4',
'title': 'When Girls Act Like D-Bags',
} }
} }
@ -22,17 +24,16 @@ def _real_extract(self, url):
embed_url = 'http://www.break.com/embed/%s' % video_id embed_url = 'http://www.break.com/embed/%s' % video_id
webpage = self._download_webpage(embed_url, video_id) webpage = self._download_webpage(embed_url, video_id)
info_json = self._search_regex(r'var embedVars = ({.*?});', webpage, info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
u'info json', flags=re.DOTALL) 'info json', flags=re.DOTALL)
info = json.loads(info_json) info = json.loads(info_json)
video_url = info['videoUri'] video_url = info['videoUri']
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url) m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
if m_youtube is not None: if m_youtube is not None:
return self.url_result(m_youtube.group(1), 'Youtube') return self.url_result(m_youtube.group(1), 'Youtube')
final_url = video_url + '?' + info['AuthToken'] final_url = video_url + '?' + info['AuthToken']
return [{ return {
'id': video_id, 'id': video_id,
'url': final_url, 'url': final_url,
'ext': determine_ext(final_url), 'title': info['contentName'],
'title': info['contentName'],
'thumbnail': info['thumbUri'], 'thumbnail': info['thumbUri'],
}] }