Add an extractor for techtalks.tv (closes #1606)

pull/980/merge
Jaime Marquínez Ferrándiz 2013-10-17 08:20:58 +02:00
parent 54ed626cf8
commit d21ab29200
2 changed files with 66 additions and 0 deletions

View File

@ -115,6 +115,7 @@ from .statigram import StatigramIE
from .steam import SteamIE
from .sztvhu import SztvHuIE
from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE
from .ted import TEDIE
from .tf1 import TF1IE
from .thisav import ThisAVIE

View File

@ -0,0 +1,65 @@
import re
from .common import InfoExtractor
from ..utils import (
get_element_by_attribute,
clean_html,
)
class TechTalksIE(InfoExtractor):
_VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/'
_TEST = {
u'url': u'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/',
u'playlist': [
{
u'file': u'57758.flv',
u'info_dict': {
u'title': u'Learning Topic Models --- Going beyond SVD',
},
},
{
u'file': u'57758-slides.flv',
u'info_dict': {
u'title': u'Learning Topic Models --- Going beyond SVD',
},
},
],
u'params': {
# rtmp download
u'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
talk_id = mobj.group('id')
webpage = self._download_webpage(url, talk_id)
rtmp_url = self._search_regex(r'netConnectionUrl: \'(.*?)\'', webpage,
u'rtmp url')
play_path = self._search_regex(r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"',
webpage, u'presenter play path')
title = clean_html(get_element_by_attribute('class', 'title', webpage))
video_info = {
'id': talk_id,
'title': title,
'url': rtmp_url,
'play_path': play_path,
'ext': 'flv',
}
m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage)
if m_slides is None:
return video_info
else:
return [
video_info,
# The slides video
{
'id': talk_id + '-slides',
'title': title,
'url': rtmp_url,
'play_path': m_slides.group(1),
'ext': 'flv',
},
]