lopar/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-14 13:27:27 +00:00
Code Releases Activity

+unicode_literals

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-01-07 09:41:13 +01:00
parent 3d3538e422
commit ecfef3e5bf
2 changed files with 52 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
test/test_playlists.py
View File

@ -1,6 +1,8 @@
#!/usr/bin/env python #!/usr/bin/env python
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import os import os
import sys import sys
@ -43,7 +45,7 @@ class TestPlaylists(unittest.TestCase):
ie = DailymotionPlaylistIE(dl) ie = DailymotionPlaylistIE(dl)
result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q') result = ie.extract('http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'SPORT') self.assertEqual(result['title'], 'SPORT')
self.assertTrue(len(result['entries']) > 20) self.assertTrue(len(result['entries']) > 20)
def test_dailymotion_user(self): def test_dailymotion_user(self):
@ -51,7 +53,7 @@ class TestPlaylists(unittest.TestCase):
ie = DailymotionUserIE(dl) ie = DailymotionUserIE(dl)
result = ie.extract('http://www.dailymotion.com/user/generation-quoi/') result = ie.extract('http://www.dailymotion.com/user/generation-quoi/')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'Génération Quoi') self.assertEqual(result['title'], 'Génération Quoi')
self.assertTrue(len(result['entries']) >= 26) self.assertTrue(len(result['entries']) >= 26)
def test_vimeo_channel(self): def test_vimeo_channel(self):
@ -59,7 +61,7 @@ class TestPlaylists(unittest.TestCase):
ie = VimeoChannelIE(dl) ie = VimeoChannelIE(dl)
result = ie.extract('http://vimeo.com/channels/tributes') result = ie.extract('http://vimeo.com/channels/tributes')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'Vimeo Tributes') self.assertEqual(result['title'], 'Vimeo Tributes')
self.assertTrue(len(result['entries']) > 24) self.assertTrue(len(result['entries']) > 24)
def test_vimeo_user(self): def test_vimeo_user(self):
@ -67,7 +69,7 @@ class TestPlaylists(unittest.TestCase):
ie = VimeoUserIE(dl) ie = VimeoUserIE(dl)
result = ie.extract('http://vimeo.com/nkistudio/videos') result = ie.extract('http://vimeo.com/nkistudio/videos')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'Nki') self.assertEqual(result['title'], 'Nki')
self.assertTrue(len(result['entries']) > 65) self.assertTrue(len(result['entries']) > 65)
def test_vimeo_album(self): def test_vimeo_album(self):
@ -75,7 +77,7 @@ class TestPlaylists(unittest.TestCase):
ie = VimeoAlbumIE(dl) ie = VimeoAlbumIE(dl)
result = ie.extract('http://vimeo.com/album/2632481') result = ie.extract('http://vimeo.com/album/2632481')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'Staff Favorites: November 2013') self.assertEqual(result['title'], 'Staff Favorites: November 2013')
self.assertTrue(len(result['entries']) > 12) self.assertTrue(len(result['entries']) > 12)
def test_vimeo_groups(self): def test_vimeo_groups(self):
@ -83,7 +85,7 @@ class TestPlaylists(unittest.TestCase):
ie = VimeoGroupsIE(dl) ie = VimeoGroupsIE(dl)
result = ie.extract('http://vimeo.com/groups/rolexawards') result = ie.extract('http://vimeo.com/groups/rolexawards')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'Rolex Awards for Enterprise') self.assertEqual(result['title'], 'Rolex Awards for Enterprise')
self.assertTrue(len(result['entries']) > 72) self.assertTrue(len(result['entries']) > 72)
def test_ustream_channel(self): def test_ustream_channel(self):
@ -91,7 +93,7 @@ class TestPlaylists(unittest.TestCase):
ie = UstreamChannelIE(dl) ie = UstreamChannelIE(dl)
result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty') result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'5124905') self.assertEqual(result['id'], '5124905')
self.assertTrue(len(result['entries']) >= 11) self.assertTrue(len(result['entries']) >= 11)
def test_soundcloud_set(self): def test_soundcloud_set(self):
@ -99,7 +101,7 @@ class TestPlaylists(unittest.TestCase):
ie = SoundcloudSetIE(dl) ie = SoundcloudSetIE(dl)
result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep') result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'The Royal Concept EP') self.assertEqual(result['title'], 'The Royal Concept EP')
self.assertTrue(len(result['entries']) >= 6) self.assertTrue(len(result['entries']) >= 6)
def test_soundcloud_user(self): def test_soundcloud_user(self):
@ -107,7 +109,7 @@ class TestPlaylists(unittest.TestCase):
ie = SoundcloudUserIE(dl) ie = SoundcloudUserIE(dl)
result = ie.extract('https://soundcloud.com/the-concept-band') result = ie.extract('https://soundcloud.com/the-concept-band')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'9615865') self.assertEqual(result['id'], '9615865')
self.assertTrue(len(result['entries']) >= 12) self.assertTrue(len(result['entries']) >= 12)
def test_livestream_event(self): def test_livestream_event(self):
@ -115,7 +117,7 @@ class TestPlaylists(unittest.TestCase):
ie = LivestreamIE(dl) ie = LivestreamIE(dl)
result = ie.extract('http://new.livestream.com/tedx/cityenglish') result = ie.extract('http://new.livestream.com/tedx/cityenglish')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'TEDCity2.0 (English)') self.assertEqual(result['title'], 'TEDCity2.0 (English)')
self.assertTrue(len(result['entries']) >= 4) self.assertTrue(len(result['entries']) >= 4)
def test_nhl_videocenter(self): def test_nhl_videocenter(self):
@ -123,8 +125,8 @@ class TestPlaylists(unittest.TestCase):
ie = NHLVideocenterIE(dl) ie = NHLVideocenterIE(dl)
result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999') result = ie.extract('http://video.canucks.nhl.com/videocenter/console?catid=999')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'999') self.assertEqual(result['id'], '999')
self.assertEqual(result['title'], u'Highlights') self.assertEqual(result['title'], 'Highlights')
self.assertEqual(len(result['entries']), 12) self.assertEqual(len(result['entries']), 12)
def test_bambuser_channel(self): def test_bambuser_channel(self):
@ -132,7 +134,7 @@ class TestPlaylists(unittest.TestCase):
ie = BambuserChannelIE(dl) ie = BambuserChannelIE(dl)
result = ie.extract('http://bambuser.com/channel/pixelversity') result = ie.extract('http://bambuser.com/channel/pixelversity')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'pixelversity') self.assertEqual(result['title'], 'pixelversity')
self.assertTrue(len(result['entries']) >= 60) self.assertTrue(len(result['entries']) >= 60)
def test_bandcamp_album(self): def test_bandcamp_album(self):
@ -140,7 +142,7 @@ class TestPlaylists(unittest.TestCase):
ie = BandcampAlbumIE(dl) ie = BandcampAlbumIE(dl)
result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep') result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['title'], u'Nightmare Night EP') self.assertEqual(result['title'], 'Nightmare Night EP')
self.assertTrue(len(result['entries']) >= 4) self.assertTrue(len(result['entries']) >= 4)
def test_smotri_community(self): def test_smotri_community(self):
@ -148,8 +150,8 @@ class TestPlaylists(unittest.TestCase):
ie = SmotriCommunityIE(dl) ie = SmotriCommunityIE(dl)
result = ie.extract('http://smotri.com/community/video/kommuna') result = ie.extract('http://smotri.com/community/video/kommuna')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'kommuna') self.assertEqual(result['id'], 'kommuna')
self.assertEqual(result['title'], u'КПРФ') self.assertEqual(result['title'], 'КПРФ')
self.assertTrue(len(result['entries']) >= 4) self.assertTrue(len(result['entries']) >= 4)
def test_smotri_user(self): def test_smotri_user(self):
@ -157,17 +159,17 @@ class TestPlaylists(unittest.TestCase):
ie = SmotriUserIE(dl) ie = SmotriUserIE(dl)
result = ie.extract('http://smotri.com/user/inspector') result = ie.extract('http://smotri.com/user/inspector')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'inspector') self.assertEqual(result['id'], 'inspector')
self.assertEqual(result['title'], u'Inspector') self.assertEqual(result['title'], 'Inspector')
self.assertTrue(len(result['entries']) >= 9) self.assertTrue(len(result['entries']) >= 9)
def test_AcademicEarthCourse(self): def test_AcademicEarthCourse(self):
dl = FakeYDL() dl = FakeYDL()
ie = AcademicEarthCourseIE(dl) ie = AcademicEarthCourseIE(dl)
result = ie.extract(u'http://academicearth.org/courses/building-dynamic-websites/') result = ie.extract('http://academicearth.org/courses/building-dynamic-websites/')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'building-dynamic-websites') self.assertEqual(result['id'], 'building-dynamic-websites')
self.assertEqual(result['title'], u'Building Dynamic Websites') self.assertEqual(result['title'], 'Building Dynamic Websites')
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"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']), 10)
@ -176,8 +178,8 @@ class TestPlaylists(unittest.TestCase):
ie = IviCompilationIE(dl) ie = IviCompilationIE(dl)
result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel') result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'dezhurnyi_angel') self.assertEqual(result['id'], 'dezhurnyi_angel')
self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012)') self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012)')
self.assertTrue(len(result['entries']) >= 36) self.assertTrue(len(result['entries']) >= 36)
def test_ivi_compilation_season(self): def test_ivi_compilation_season(self):
@ -185,8 +187,8 @@ class TestPlaylists(unittest.TestCase):
ie = IviCompilationIE(dl) ie = IviCompilationIE(dl)
result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2') result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'dezhurnyi_angel/season2') self.assertEqual(result['id'], 'dezhurnyi_angel/season2')
self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012) 2 сезон') self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 2 сезон')
self.assertTrue(len(result['entries']) >= 20) self.assertTrue(len(result['entries']) >= 20)
def test_imdb_list(self): def test_imdb_list(self):
@ -194,8 +196,8 @@ class TestPlaylists(unittest.TestCase):
ie = ImdbListIE(dl) ie = ImdbListIE(dl)
result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U') result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'sMjedvGDd8U') self.assertEqual(result['id'], 'sMjedvGDd8U')
self.assertEqual(result['title'], u'Animated and Family Films') self.assertEqual(result['title'], 'Animated and Family Films')
self.assertTrue(len(result['entries']) >= 48) self.assertTrue(len(result['entries']) >= 48)
def test_khanacademy_topic(self): def test_khanacademy_topic(self):
@ -203,9 +205,9 @@ class TestPlaylists(unittest.TestCase):
ie = KhanAcademyIE(dl) ie = KhanAcademyIE(dl)
result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography') result = ie.extract('https://www.khanacademy.org/math/applied-math/cryptography')
self.assertIsPlaylist(result) self.assertIsPlaylist(result)
self.assertEqual(result['id'], u'cryptography') self.assertEqual(result['id'], 'cryptography')
self.assertEqual(result['title'], u'Journey into cryptography') self.assertEqual(result['title'], 'Journey into cryptography')
self.assertEqual(result['description'], u'How have humans protected their secret messages through history? What has changed today?') self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?')
self.assertTrue(len(result['entries']) >= 3) self.assertTrue(len(result['entries']) >= 3)

35
youtube_dl/extractor/imdb.py
View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
import json import json
@ -9,18 +11,18 @@ from ..utils import (
class ImdbIE(InfoExtractor): class ImdbIE(InfoExtractor):
IE_NAME = u'imdb' IE_NAME = 'imdb'
IE_DESC = u'Internet Movie Database trailers' IE_DESC = 'Internet Movie Database trailers'
_VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)' _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
_TEST = { _TEST = {
u'url': u'http://www.imdb.com/video/imdb/vi2524815897', 'url': 'http://www.imdb.com/video/imdb/vi2524815897',
u'md5': u'9f34fa777ade3a6e57a054fdbcb3a068', 'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
u'info_dict': { 'info_dict': {
u'id': u'2524815897', 'id': '2524815897',
u'ext': u'mp4', 'ext': 'mp4',
u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb', 'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
u'description': u'md5:9061c2219254e5d14e03c25c98e96a81', 'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
} }
} }
@ -37,10 +39,10 @@ class ImdbIE(InfoExtractor):
f_path = f_path.strip() f_path = f_path.strip()
format_page = self._download_webpage( format_page = self._download_webpage(
compat_urlparse.urljoin(url, f_path), compat_urlparse.urljoin(url, f_path),
u'Downloading info for %s format' % f_id) 'Downloading info for %s format' % f_id)
json_data = self._search_regex( json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>', r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
format_page, u'json data', flags=re.DOTALL) format_page, 'json data', flags=re.DOTALL)
info = json.loads(json_data) info = json.loads(json_data)
format_info = info['videoPlayerObject']['video'] format_info = info['videoPlayerObject']['video']
formats.append({ formats.append({
@ -56,9 +58,10 @@ class ImdbIE(InfoExtractor):
'thumbnail': format_info['slate'], 'thumbnail': format_info['slate'],
} }
class ImdbListIE(InfoExtractor): class ImdbListIE(InfoExtractor):
IE_NAME = u'imdb:list' IE_NAME = 'imdb:list'
IE_DESC = u'Internet Movie Database lists' IE_DESC = 'Internet Movie Database lists'
_VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})' _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
def _real_extract(self, url): def _real_extract(self, url):
@ -66,13 +69,13 @@ class ImdbListIE(InfoExtractor):
list_id = mobj.group('id') list_id = mobj.group('id')
# RSS XML is sometimes malformed # RSS XML is sometimes malformed
rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, u'Downloading list RSS') rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, 'Downloading list RSS')
list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, u'list title') list_title = self._html_search_regex(r'<title>(.*?)</title>', rss, 'list title')
# Export is independent of actual author_id, but returns 404 if no author_id is provided. # Export is independent of actual author_id, but returns 404 if no author_id is provided.
# However, passing dummy author_id seems to be enough. # However, passing dummy author_id seems to be enough.
csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id, csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id,
list_id, u'Downloading list CSV') list_id, 'Downloading list CSV')
entries = [] entries = []
for item in csv.split('\n')[1:]: for item in csv.split('\n')[1:]: