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

[vimeo] Use unicode_literals

Browse source
This commit is contained in:
Philipp Hagemeister 2014-01-06 23:38:16 +01:00
parent 559e370f44
commit 9148eb002b
1 changed files with 60 additions and 57 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

117
youtube_dl/extractor/vimeo.py
View file

@ -1,4 +1,6 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals
import json import json
import re import re
import itertools import itertools
@ -31,54 +33,55 @@ class VimeoIE(InfoExtractor):
(?P<id>[0-9]+) (?P<id>[0-9]+)
/?(?:[?&].*)?(?:[#].*)?$''' /?(?:[?&].*)?(?:[#].*)?$'''
_NETRC_MACHINE = 'vimeo' _NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo' IE_NAME = 'vimeo'
_TESTS = [ _TESTS = [
{ {
u'url': u'http://vimeo.com/56015672#at=0', 'url': 'http://vimeo.com/56015672#at=0',
u'file': u'56015672.mp4', 'file': '56015672.mp4',
u'md5': u'8879b6cc097e987f02484baf890129e5', 'md5': '8879b6cc097e987f02484baf890129e5',
u'info_dict': { 'info_dict': {
u"upload_date": u"20121220", "upload_date": "20121220",
u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
u"uploader_id": u"user7108434", "uploader_id": "user7108434",
u"uploader": u"Filippo Valsorda", "uploader": "Filippo Valsorda",
u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
}, },
}, },
{ {
u'url': u'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
u'file': u'68093876.mp4', 'file': '68093876.mp4',
u'md5': u'3b5ca6aa22b60dfeeadf50b72e44ed82', 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
u'note': u'Vimeo Pro video (#1197)', 'note': 'Vimeo Pro video (#1197)',
u'info_dict': { 'info_dict': {
u'uploader_id': u'openstreetmapus', 'uploader_id': 'openstreetmapus',
u'uploader': u'OpenStreetMap US', 'uploader': 'OpenStreetMap US',
u'title': u'Andy Allan - Putting the Carto into OpenStreetMap Cartography', 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
}, },
}, },
{ {
u'url': u'http://player.vimeo.com/video/54469442', 'url': 'http://player.vimeo.com/video/54469442',
u'file': u'54469442.mp4', 'file': '54469442.mp4',
u'md5': u'619b811a4417aa4abe78dc653becf511', 'md5': '619b811a4417aa4abe78dc653becf511',
u'note': u'Videos that embed the url in the player page', 'note': 'Videos that embed the url in the player page',
u'info_dict': { 'info_dict': {
u'title': u'Kathy Sierra: Building the minimum Badass User, Business of Software', 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software',
u'uploader': u'The BLN & Business of Software', 'uploader': 'The BLN & Business of Software',
'uploader_id': 'theblnbusinessofsoftware',
}, },
}, },
{ {
u'url': u'http://vimeo.com/68375962', 'url': 'http://vimeo.com/68375962',
u'file': u'68375962.mp4', 'file': '68375962.mp4',
u'md5': u'aaf896bdb7ddd6476df50007a0ac0ae7', 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
u'note': u'Video protected with password', 'note': 'Video protected with password',
u'info_dict': { 'info_dict': {
u'title': u'youtube-dl password protected test video', 'title': 'youtube-dl password protected test video',
u'upload_date': u'20130614', 'upload_date': '20130614',
u'uploader_id': u'user18948128', 'uploader_id': 'user18948128',
u'uploader': u'Jaime Marquínez Ferrándiz', 'uploader': 'Jaime Marquínez Ferrándiz',
}, },
u'params': { 'params': {
u'videopassword': u'youtube-dl', 'videopassword': 'youtube-dl',
}, },
}, },
] ]
@ -100,12 +103,12 @@ class VimeoIE(InfoExtractor):
login_request = compat_urllib_request.Request(login_url, data) login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
login_request.add_header('Cookie', 'xsrft=%s' % token) login_request.add_header('Cookie', 'xsrft=%s' % token)
self._download_webpage(login_request, None, False, u'Wrong login info') self._download_webpage(login_request, None, False, 'Wrong login info')
def _verify_video_password(self, url, video_id, webpage): def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None) password = self._downloader.params.get('videopassword', None)
if password is None: if password is None:
raise ExtractorError(u'This video is protected by a password, use the --video-password option') raise ExtractorError('This video is protected by a password, use the --video-password option')
token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1) token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1)
data = compat_urllib_parse.urlencode({'password': password, data = compat_urllib_parse.urlencode({'password': password,
'token': token}) 'token': token})
@ -118,8 +121,8 @@ class VimeoIE(InfoExtractor):
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
password_request.add_header('Cookie', 'xsrft=%s' % token) password_request.add_header('Cookie', 'xsrft=%s' % token)
self._download_webpage(password_request, video_id, self._download_webpage(password_request, video_id,
u'Verifying the password', 'Verifying the password',
u'Wrong password') 'Wrong password')
def _real_initialize(self): def _real_initialize(self):
self._login() self._login()
@ -134,7 +137,7 @@ class VimeoIE(InfoExtractor):
# Extract ID from URL # Extract ID from URL
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError('Invalid URL: %s' % url)
video_id = mobj.group('id') video_id = mobj.group('id')
if mobj.group('pro') or mobj.group('player'): if mobj.group('pro') or mobj.group('player'):
@ -155,7 +158,7 @@ class VimeoIE(InfoExtractor):
try: try:
try: try:
config_url = self._html_search_regex( config_url = self._html_search_regex(
r' data-config-url="(.+?)"', webpage, u'config URL') r' data-config-url="(.+?)"', webpage, 'config URL')
config_json = self._download_webpage(config_url, video_id) config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json) config = json.loads(config_json)
except RegexNotFoundError: except RegexNotFoundError:
@ -166,18 +169,18 @@ class VimeoIE(InfoExtractor):
config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1)) config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1))
else: else:
config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
config = self._search_regex(config_re, webpage, u'info section', config = self._search_regex(config_re, webpage, 'info section',
flags=re.DOTALL) flags=re.DOTALL)
config = json.loads(config) config = json.loads(config)
except Exception as e: except Exception as e:
if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option') raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
if re.search('<form[^>]+?id="pw_form"', webpage) is not None: if re.search('<form[^>]+?id="pw_form"', webpage) is not None:
self._verify_video_password(url, video_id, webpage) self._verify_video_password(url, video_id, webpage)
return self._real_extract(url) return self._real_extract(url)
else: else:
raise ExtractorError(u'Unable to extract info section', raise ExtractorError('Unable to extract info section',
cause=e) cause=e)
else: else:
if config.get('view') == 4: if config.get('view') == 4:
@ -216,9 +219,9 @@ class VimeoIE(InfoExtractor):
video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
try: try:
view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, u'view count')) view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, u'like count')) like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, u'comment count')) comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
except RegexNotFoundError: except RegexNotFoundError:
# This info is only available in vimeo.com/{id} urls # This info is only available in vimeo.com/{id} urls
view_count = None view_count = None
@ -259,7 +262,7 @@ class VimeoIE(InfoExtractor):
for key in ('other', 'sd', 'hd'): for key in ('other', 'sd', 'hd'):
formats += files[key] formats += files[key]
if len(formats) == 0: if len(formats) == 0:
raise ExtractorError(u'No known codec found') raise ExtractorError('No known codec found')
return { return {
'id': video_id, 'id': video_id,
@ -278,7 +281,7 @@ class VimeoIE(InfoExtractor):
class VimeoChannelIE(InfoExtractor): class VimeoChannelIE(InfoExtractor):
IE_NAME = u'vimeo:channel' IE_NAME = 'vimeo:channel'
_VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)' _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"' _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
_TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
@ -287,14 +290,14 @@ class VimeoChannelIE(InfoExtractor):
return '%s/videos/page:%d/' % (base_url, pagenum) return '%s/videos/page:%d/' % (base_url, pagenum)
def _extract_list_title(self, webpage): def _extract_list_title(self, webpage):
return self._html_search_regex(self._TITLE_RE, webpage, u'list title') return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
def _extract_videos(self, list_id, base_url): def _extract_videos(self, list_id, base_url):
video_ids = [] video_ids = []
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
webpage = self._download_webpage( webpage = self._download_webpage(
self._page_url(base_url, pagenum) ,list_id, self._page_url(base_url, pagenum) ,list_id,
u'Downloading page %s' % pagenum) 'Downloading page %s' % pagenum)
video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break break
@ -314,7 +317,7 @@ class VimeoChannelIE(InfoExtractor):
class VimeoUserIE(VimeoChannelIE): class VimeoUserIE(VimeoChannelIE):
IE_NAME = u'vimeo:user' IE_NAME = 'vimeo:user'
_VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)(?:[#?]|$)' _VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)(?:[#?]|$)'
_TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
@ -331,7 +334,7 @@ class VimeoUserIE(VimeoChannelIE):
class VimeoAlbumIE(VimeoChannelIE): class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = u'vimeo:album' IE_NAME = 'vimeo:album'
_VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)' _VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)'
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
@ -345,7 +348,7 @@ class VimeoAlbumIE(VimeoChannelIE):
class VimeoGroupsIE(VimeoAlbumIE): class VimeoGroupsIE(VimeoAlbumIE):
IE_NAME = u'vimeo:group' IE_NAME = 'vimeo:group'
_VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P<name>[^/]+)' _VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P<name>[^/]+)'
def _extract_list_title(self, webpage): def _extract_list_title(self, webpage):
@ -358,8 +361,8 @@ class VimeoGroupsIE(VimeoAlbumIE):
class VimeoReviewIE(InfoExtractor): class VimeoReviewIE(InfoExtractor):
IE_NAME = u'vimeo:review' IE_NAME = 'vimeo:review'
IE_DESC = u'Review pages on vimeo' IE_DESC = 'Review pages on vimeo'
_VALID_URL = r'(?:https?://)?vimeo.\com/[^/]+/review/(?P<id>[^/]+)' _VALID_URL = r'(?:https?://)?vimeo.\com/[^/]+/review/(?P<id>[^/]+)'
_TEST = { _TEST = {
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',