w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[nationalgeographic] improve extraction

Browse source
This commit is contained in:
remitamine 2016-03-31 13:44:55 +01:00
parent dd17041c82
commit d84b48e3f1
1 changed files with 15 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
youtube_dl/extractor/nationalgeographic.py
View file

@ -8,14 +8,16 @@ from ..utils import (
class NationalGeographicIE(InfoExtractor): class NationalGeographicIE(InfoExtractor):
IE_NAME = 'natgeo'
_VALID_URL = r'https?://video\.nationalgeographic\.com/.*?' _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?'
_TESTS = [ _TESTS = [
{ {
'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo', 'url': 'http://video.nationalgeographic.com/video/news/150210-news-crab-mating-vin?source=featuredvideo',
'md5': '730855d559abbad6b42c2be1fa584917',
'info_dict': { 'info_dict': {
'id': '4DmDACA6Qtk_', 'id': '0000014b-70a1-dd8c-af7f-f7b559330001',
'ext': 'flv', 'ext': 'mp4',
'title': 'Mating Crabs Busted by Sharks', 'title': 'Mating Crabs Busted by Sharks',
'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3', 'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3',
}, },
@ -23,9 +25,10 @@ class NationalGeographicIE(InfoExtractor):
}, },
{ {
'url': 'http://video.nationalgeographic.com/wild/when-sharks-attack/the-real-jaws', 'url': 'http://video.nationalgeographic.com/wild/when-sharks-attack/the-real-jaws',
'md5': '6a3105eb448c070503b3105fb9b320b5',
'info_dict': { 'info_dict': {
'id': '_JeBD_D7PlS5', 'id': 'ngc-I0IauNSWznb_UV008GxSbwY35BZvgi2e',
'ext': 'flv', 'ext': 'mp4',
'title': 'The Real Jaws', 'title': 'The Real Jaws',
'description': 'md5:8d3e09d9d53a85cd397b4b21b2c77be6', 'description': 'md5:8d3e09d9d53a85cd397b4b21b2c77be6',
}, },
@ -37,18 +40,15 @@ class NationalGeographicIE(InfoExtractor):
name = url_basename(url) name = url_basename(url)
webpage = self._download_webpage(url, name) webpage = self._download_webpage(url, name)
feed_url = self._search_regex(
r'data-feed-url="([^"]+)"', webpage, 'feed url')
guid = self._search_regex( guid = self._search_regex(
r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"', r'id="(?:videoPlayer|player-container)"[^>]+data-guid="([^"]+)"',
webpage, 'guid') webpage, 'guid')
feed = self._download_xml('%s?byGuid=%s' % (feed_url, guid), name) return {
content = feed.find('.//{http://search.yahoo.com/mrss/}content') '_type': 'url_transparent',
theplatform_id = url_basename(content.attrib.get('url')) 'ie_key': 'ThePlatform',
'url': smuggle_url(
return self.url_result(smuggle_url( 'http://link.theplatform.com/s/ngs/media/guid/2423130747/%s?mbr=true' % guid,
'http://link.theplatform.com/s/ngs/%s?formats=MPEG4&manifest=f4m' % theplatform_id, {'force_smil_url': True}),
# For some reason, the normal links don't work and we must force 'id': guid,
# the use of f4m }
{'force_smil_url': True}))