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

[safari] Relax url regexes (Closes #10202)

Browse source
This commit is contained in:
Sergey M․ 2016-08-01 21:48:48 +07:00
parent e382b953f0
commit 697655a7c0
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
youtube_dl/extractor/safari.py
View file

@ -75,7 +75,7 @@ class SafariBaseIE(InfoExtractor):
class SafariIE(SafariBaseIE): class SafariIE(SafariBaseIE):
IE_NAME = 'safari' IE_NAME = 'safari'
IE_DESC = 'safaribooksonline.com online video' IE_DESC = 'safaribooksonline.com online video'
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>part\d+)\.html' _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
_TESTS = [{ _TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html', 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
@ -92,6 +92,9 @@ class SafariIE(SafariBaseIE):
# non-digits in course id # non-digits in course id
'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html', 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -132,12 +135,15 @@ class SafariIE(SafariBaseIE):
class SafariApiIE(SafariBaseIE): class SafariApiIE(SafariBaseIE):
IE_NAME = 'safari:api' IE_NAME = 'safari:api'
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>part\d+)\.html' _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
_TEST = { _TESTS = [{
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
'only_matching': True, 'only_matching': True,
} }, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)