midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[firstpost] Fix extraction

Browse source
This commit is contained in:
Sergey M․ 2014-04-11 20:40:42 +07:00
parent 0d3070d364
commit 6a4f3528c8
1 changed files with 19 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
youtube_dl/extractor/firstpost.py
View file

@ -6,7 +6,6 @@ from .common import InfoExtractor
class FirstpostIE(InfoExtractor): class FirstpostIE(InfoExtractor):
IE_NAME = 'Firstpost.com'
_VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html' _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
_TEST = { _TEST = {
@ -16,7 +15,6 @@ class FirstpostIE(InfoExtractor):
'id': '1025403', 'id': '1025403',
'ext': 'mp4', 'ext': 'mp4',
'title': 'India to launch indigenous aircraft carrier INS Vikrant today', 'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.',
} }
} }
@ -24,15 +22,26 @@ class FirstpostIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) data = self._download_xml(
video_url = self._html_search_regex( 'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
r'<div.*?name="div_video".*?flashvars="([^"]+)">', 'Downloading video XML')
webpage, 'video URL')
item = data.find('./playlist/item')
thumbnail = item.find('./image').text
title = item.find('./title').text
formats = [
{
'url': details.find('./file').text,
'format_id': details.find('./label').text.strip(),
'width': int(details.find('./width').text.strip()),
'height': int(details.find('./height').text.strip()),
} for details in item.findall('./source/file_details') if details.find('./file').text
]
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'title': title,
'title': self._og_search_title(webpage), 'thumbnail': thumbnail,
'description': self._og_search_description(webpage), 'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage),
} }