gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[academicearth] Fix extraction

Browse source 
The courses seems to be no longer available, changed the test to a playlist.
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-24 14:18:12 +01:00
parent cd7ee7aa44
commit 9e57ce716f
2 changed files with 10 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
test/test_playlists.py
View file

@ -170,12 +170,12 @@ class TestPlaylists(unittest.TestCase):
def test_AcademicEarthCourse(self): def test_AcademicEarthCourse(self):
dl = FakeYDL() dl = FakeYDL()
ie = AcademicEarthCourseIE(dl) ie = AcademicEarthCourseIE(dl)
result = ie.extract('http://academicearth.org/courses/building-dynamic-websites/') result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'building-dynamic-websites') self.assertEqual(result['id'], 'laws-of-nature')
self.assertEqual(result['title'], 'Building Dynamic Websites') self.assertEqual(result['title'], 'Laws of Nature')
self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.") self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
self.assertEqual(len(result['entries']), 10) self.assertEqual(len(result['entries']), 4)
def test_ivi_compilation(self): def test_ivi_compilation(self):
dl = FakeYDL() dl = FakeYDL()

9
youtube_dl/extractor/academicearth.py
View file

@ -5,7 +5,7 @@ from .common import InfoExtractor
class AcademicEarthCourseIE(InfoExtractor): class AcademicEarthCourseIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)' _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
IE_NAME = 'AcademicEarth:Course' IE_NAME = 'AcademicEarth:Course'
def _real_extract(self, url): def _real_extract(self, url):
@ -14,12 +14,13 @@ class AcademicEarthCourseIE(InfoExtractor):
webpage = self._download_webpage(url, playlist_id) webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex( title = self._html_search_regex(
r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title') r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
description = self._html_search_regex( description = self._html_search_regex(
r'<p class="excerpt">(.*?)</p>', r'<p class="excerpt"[^>]*?>(.*?)</p>',
webpage, u'description', fatal=False) webpage, u'description', fatal=False)
print(description)
urls = re.findall( urls = re.findall(
r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">', r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
webpage) webpage)
entries = [self.url_result(u) for u in urls] entries = [self.url_result(u) for u in urls]