X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvimeo.py;h=ef90fecc07b596c70f4ff6f3ff2cbb7c6fc86092;hb=a93cc0d9435fca79787369d3670fce0742ae47ef;hp=cea29f03525af91d1be56c475da0f62ce45eea83;hpb=4f41664de8e0486127d8dd16168d829c26f79fdf;p=youtube-dl diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index cea29f035..ef90fecc0 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -1,3 +1,4 @@ +# encoding: utf-8 import json import re import itertools @@ -10,7 +11,9 @@ from ..utils import ( clean_html, get_element_by_attribute, ExtractorError, + RegexNotFoundError, std_headers, + unsmuggle_url, ) class VimeoIE(InfoExtractor): @@ -24,7 +27,7 @@ class VimeoIE(InfoExtractor): { u'url': u'http://vimeo.com/56015672', u'file': u'56015672.mp4', - u'md5': u'8879b6cc097e987f02484baf890129e5', + u'md5': u'ae7a1d8b183758a0506b0622f37dfa14', u'info_dict': { u"upload_date": u"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", @@ -54,6 +57,21 @@ class VimeoIE(InfoExtractor): u'uploader': u'The BLN & Business of Software', }, }, + { + u'url': u'http://vimeo.com/68375962', + u'file': u'68375962.mp4', + u'md5': u'aaf896bdb7ddd6476df50007a0ac0ae7', + u'note': u'Video protected with password', + u'info_dict': { + u'title': u'youtube-dl password protected test video', + u'upload_date': u'20130614', + u'uploader_id': u'user18948128', + u'uploader': u'Jaime MarquÃnez Ferrándiz', + }, + u'params': { + u'videopassword': u'youtube-dl', + }, + }, ] def _login(self): @@ -98,6 +116,12 @@ class VimeoIE(InfoExtractor): self._login() def _real_extract(self, url, new_video=True): + url, data = unsmuggle_url(url) + headers = std_headers + if data is not None: + headers = headers.copy() + headers.update(data) + # Extract ID from URL mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -112,7 +136,7 @@ class VimeoIE(InfoExtractor): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url, None, std_headers) + request = compat_urllib_request.Request(url, None, headers) webpage = self._download_webpage(request, video_id) # Now we begin extracting as much information as we can from what we @@ -122,18 +146,26 @@ class VimeoIE(InfoExtractor): # Extract the config JSON try: - config = self._search_regex([r' = {config:({.+?}),assets:', r'c=({.+?);'], - webpage, u'info section', flags=re.DOTALL) - config = json.loads(config) - except: + try: + config_url = self._html_search_regex( + r' data-config-url="(.+?)"', webpage, u'config URL') + config_json = self._download_webpage(config_url, video_id) + config = json.loads(config_json) + except RegexNotFoundError: + # For pro videos or player.vimeo.com urls + config = self._search_regex([r' = {config:({.+?}),assets:', r'c=({.+?);'], + webpage, u'info section', flags=re.DOTALL) + config = json.loads(config) + except Exception as e: 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') - if re.search('If so please provide the correct password.', webpage): + if re.search('