R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

made changes to fivethirtyeight extractor from PR

Browse Source
This commit is contained in:
bikeseat 2015-09-15 12:43:14 -07:00
parent 7c4f048940
commit 0b3bf20393
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
youtube_dl/extractor/fivethirtyeight.py
View File

@ -7,7 +7,7 @@ from youtube_dl import utils
class FivethirtyeightIE(InfoExtractor): class FivethirtyeightIE(InfoExtractor):
_VALID_URL = r'http://fivethirtyeight\.com/.+' _VALID_URL = r'https?://fivethirtyeight\.com/.+/(?P<id>.+?)/'
_TEST = { _TEST = {
'url': 'http://fivethirtyeight.com/features/rage-against-the-machines/', 'url': 'http://fivethirtyeight.com/features/rage-against-the-machines/',
'md5': 'c825a057981316c4d4444fefea35a108', 'md5': 'c825a057981316c4d4444fefea35a108',
@ -21,19 +21,20 @@ class FivethirtyeightIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
webpage = self._download_webpage(url, 'video_id') display_id = self._match_id(url)
video_id = self._html_search_regex(r'.*data-video-id=\'(.*)\' data-cms.*', webpage, 'video_id') webpage = self._download_webpage(url, display_id)
title = self._html_search_regex(r'<title>(.*)\s*\|', webpage, 'title') video_id = self._html_search_regex(r'data-video-id=\'(.+?)\' data-cms', webpage, display_id)
title = self._html_search_regex(r'<title>(.+?)\s*\|', webpage, 'title')
data = self._download_json( data = self._download_json(
'http://espn.go.com/videohub/video/util/getMinifiedClipJsonById?id=%s&cms=espn&device=mobile&omniReportSuite=wdgespvideo,wdgespfivethirtyeight,wdgespge&xhr=1' % video_id, video_id) 'http://espn.go.com/videohub/video/util/getMinifiedClipJsonById?id=%s&cms=espn&device=mobile&omniReportSuite=wdgespvideo,wdgespfivethirtyeight,wdgespge&xhr=1' % video_id, display_id)
url = data["videos"][0]["links"]["mobile"]["href"] url = data["videos"][0]["links"]["mobile"]["href"]
request = compat_urllib_request.Request(url) request = compat_urllib_request.Request(url)
request.add_header('User-Agent', 'ipad') request.add_header('User-Agent', 'ipad')
formats = self._extract_m3u8_formats(request, 'display_id', 'mp4') formats = self._extract_m3u8_formats(request, display_id, 'mp4')
formats[0]["url"] = request.get_full_url() formats[0]["url"] = request.get_full_url()