diff options
author | Sergey M․ <dstftw@gmail.com> | 2016-08-01 21:48:48 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2016-08-01 21:48:48 +0700 |
commit | 697655a7c0c1469dd7474714652025961e82bd69 (patch) | |
tree | fdd3716a7e973fc00f123e0f36b515086fe2de37 /youtube_dl/extractor/safari.py | |
parent | e382b953f00982a2085d3e0b1b6fb4d2a0f2db7e (diff) |
[safari] Relax url regexes (Closes #10202)
Diffstat (limited to 'youtube_dl/extractor/safari.py')
-rw-r--r-- | youtube_dl/extractor/safari.py | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 6ba91f202..08ddbe3c4 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -75,7 +75,7 @@ class SafariBaseIE(InfoExtractor): class SafariIE(SafariBaseIE): IE_NAME = 'safari' 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 = [{ '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 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html', '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): @@ -132,12 +135,15 @@ class SafariIE(SafariBaseIE): class SafariApiIE(SafariBaseIE): 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', 'only_matching': True, - } + }, { + 'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) |