github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[nextmedia] Support redirected URLs

Browse source
This commit is contained in:
Yen Chi Hsuan 2017-01-22 02:06:34 +08:00
parent 04a3d4d234
commit 7c20b7484c
No known key found for this signature in database
GPG key ID: 7F902A182457CA23
2 changed files with 13 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
ChangeLog
View file

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
+ [nextmedia] Support redirected URLs
+ [cspan] Support Ustream embedded videos (#11547) + [cspan] Support Ustream embedded videos (#11547)

13
youtube_dl/extractor/nextmedia.py
View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import parse_iso8601 from ..utils import parse_iso8601
@ -30,6 +31,12 @@ def _real_extract(self, url):
return self._extract_from_nextmedia_page(news_id, url, page) return self._extract_from_nextmedia_page(news_id, url, page)
def _extract_from_nextmedia_page(self, news_id, url, page): def _extract_from_nextmedia_page(self, news_id, url, page):
redirection_url = self._search_regex(
r'window\.location\.href\s*=\s*([\'"])(?P<url>(?!\1).+)\1',
page, 'redirection URL', default=None, group='url')
if redirection_url:
return self.url_result(compat_urlparse.urljoin(url, redirection_url))
title = self._fetch_title(page) title = self._fetch_title(page)
video_url = self._search_regex(self._URL_PATTERN, page, 'video url') video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
@ -93,7 +100,7 @@ def _real_extract(self, url):
class AppleDailyIE(NextMediaIE): class AppleDailyIE(NextMediaIE):
IE_DESC = '臺灣蘋果日報' IE_DESC = '臺灣蘋果日報'
_VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?' _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/[^/]+/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
_TESTS = [{ _TESTS = [{
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694', 'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d', 'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@ -157,6 +164,10 @@ class AppleDailyIE(NextMediaIE):
}, { }, {
'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/', 'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
'only_matching': True, 'only_matching': True,
}, {
# Redirected from http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694
'url': 'http://ent.appledaily.com.tw/section/article/headline/20150128/36354694',
'only_matching': True,
}] }]
_URL_PATTERN = r'\{url: \'(.+)\'\}' _URL_PATTERN = r'\{url: \'(.+)\'\}'