[lecture2go] Support more formats

pull/6337/head
Yen Chi Hsuan 2015-07-22 22:39:46 +08:00
parent 981b9cdc8c
commit 795704f0f1
1 changed files with 19 additions and 2 deletions

View File

@ -1,7 +1,10 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import determine_ext
class Lecture2GoIE(InfoExtractor): class Lecture2GoIE(InfoExtractor):
@ -22,12 +25,26 @@ class Lecture2GoIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<em[^>]+class="title">(.+)</em>', webpage, 'title') title = self._html_search_regex(r'<em[^>]+class="title">(.+)</em>', webpage, 'title')
video_url = self._search_regex(r'b.isFirefox..a.useHTML5\).b.setOption.a,"src","(.*.mp4)"\).else', webpage, 'video_url')
formats = []
for url in set(re.findall(r'"src","([^"]+)"', webpage)):
ext = determine_ext(url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(url, video_id))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(url, video_id))
else:
formats.append({
'url': url,
})
self._sort_formats(formats)
creator = self._html_search_regex(r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator') creator = self._html_search_regex(r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator')
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'formats': formats,
'creator': creator 'creator': creator
} }