fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[restudy] Simplify and extract all formats

This commit is contained in:
Sergey M․ 2014-12-14 03:41:00 +06:00
parent 4a0132c570
commit ac265bef1e
1 changed files with 18 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
youtube_dl/extractor/restudy.py
View File

@ -5,37 +5,36 @@ from .common import InfoExtractor
class RestudyIE(InfoExtractor): class RestudyIE(InfoExtractor):
_VALID_URL = r'https://www.restudy.dk/video/play/id/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?restudy\.dk/video/play/id/(?P<id>[0-9]+)'
_TEST = { _TEST = {
'url': 'https://www.restudy.dk/video/play/id/1637', 'url': 'https://www.restudy.dk/video/play/id/1637',
# MD5 sum of first 10241 bytes of the video file, as reported by
# head -c 10241 Leiden-frosteffekt-1637.mp4 | md5sum
'md5': '4e755c4287f292a1fe5363834a683818',
'info_dict': { 'info_dict': {
'id': '1637', 'id': '1637',
'ext': 'mp4', 'ext': 'flv',
'title': 'Leiden-frosteffekt', 'title': 'Leiden-frosteffekt',
'description': 'Denne video er et eksperiment med flydende kvælstof.',
},
'params': {
# rtmp download
'skip_download': True,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
xml_url = (
'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml'
% video_id)
xml = self._download_webpage(xml_url, video_id)
base = self._search_regex( webpage = self._download_webpage(url, video_id)
r'<meta base="([^"]+)', xml, 'meta base')
# TODO: Provide multiple video qualities instead of forcing highest title = self._og_search_title(webpage).strip()
filename = self._search_regex( description = self._og_search_description(webpage).strip()
r'<video src="mp4:([^"]+_high\.mp4)', xml, 'filename')
url = '%s%s' % (base, filename) formats = self._extract_smil_formats(
title = self._og_search_title(webpage) 'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id,
video_id)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': url, 'description': description,
'protocol': 'rtmp', 'formats': formats,
} }