minhngoc25a
/
yt-dlc
mirror of https://github.com/blackjack4494/yt-dlc
1
0
Fork 1
Code Issues Releases Wiki Activity

[washingtonpost] Modernize and correct test case

This commit is contained in:
Philipp Hagemeister 2015-01-07 11:21:40 +01:00
parent e9a537774d
commit 99673f04bc
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
youtube_dl/extractor/washingtonpost.py
View File

@ -10,14 +10,14 @@ from ..utils import (
class WashingtonPostIE(InfoExtractor): class WashingtonPostIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' _VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])'
_TEST = { _TEST = {
'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/',
'info_dict': { 'info_dict': {
'title': 'Sinkhole of bureaucracy', 'title': 'Sinkhole of bureaucracy',
}, },
'playlist': [{ 'playlist': [{
'md5': 'c3f4b4922ffa259243f68e928db2db8c', 'md5': '79132cc09ec5309fa590ae46e4cc31bc',
'info_dict': { 'info_dict': {
'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f', 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f',
'ext': 'mp4', 'ext': 'mp4',
@ -29,7 +29,7 @@ class WashingtonPostIE(InfoExtractor):
'upload_date': '20140322', 'upload_date': '20140322',
}, },
}, { }, {
'md5': 'f645a07652c2950cd9134bb852c5f5eb', 'md5': 'e1d5734c06865cc504ad99dc2de0d443',
'info_dict': { 'info_dict': {
'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f', 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f',
'ext': 'mp4', 'ext': 'mp4',
@ -44,10 +44,9 @@ class WashingtonPostIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) page_id = self._match_id(url)
page_id = mobj.group('id')
webpage = self._download_webpage(url, page_id) webpage = self._download_webpage(url, page_id)
title = self._og_search_title(webpage) title = self._og_search_title(webpage)
uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage) uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage)
entries = [] entries = []