From b3d14cbfa7d593a74cf1423ec58265abff6758a3 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 20:18:21 +0200 Subject: [PATCH] Move Vimeo into its own file --- youtube_dl/InfoExtractors.py | 125 +----------------------------- youtube_dl/extractor/vimeo.py | 138 ++++++++++++++++++++++++++++++++++ 2 files changed, 139 insertions(+), 124 deletions(-) create mode 100644 youtube_dl/extractor/vimeo.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 68e21c6354..f06a8e0c91 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -28,6 +28,7 @@ from .extractor.dailymotion import DailymotionIE from .extractor.metacafe import MetacafeIE from .extractor.statigram import StatigramIE from .extractor.photobucket import PhotobucketIE +from .extractor.vimeo import VimeoIE from .extractor.yahoo import YahooIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeUserIE, YoutubeChannelIE @@ -37,130 +38,6 @@ from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeUserIE, Yout -class VimeoIE(InfoExtractor): - """Information extractor for vimeo.com.""" - - # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' - IE_NAME = u'vimeo' - - def _verify_video_password(self, url, video_id, webpage): - password = self._downloader.params.get('password', None) - if password is None: - raise ExtractorError(u'This video is protected by a password, use the --password option') - token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1) - data = compat_urllib_parse.urlencode({'password': password, - 'token': token}) - # I didn't manage to use the password with https - if url.startswith('https'): - pass_url = url.replace('https','http') - else: - pass_url = url - password_request = compat_urllib_request.Request(pass_url+'/password', data) - password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - password_request.add_header('Cookie', 'xsrft=%s' % token) - pass_web = self._download_webpage(password_request, video_id, - u'Verifying the password', - u'Wrong password') - - def _real_extract(self, url, new_video=True): - # Extract ID from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group('id') - if not mobj.group('proto'): - url = 'https://' + url - if mobj.group('direct_link') or mobj.group('pro'): - url = 'https://vimeo.com/' + video_id - - # Retrieve video webpage to extract further information - request = compat_urllib_request.Request(url, None, std_headers) - webpage = self._download_webpage(request, video_id) - - # Now we begin extracting as much information as we can from what we - # retrieved. First we extract the information common to all extractors, - # and latter we extract those that are Vimeo specific. - self.report_extraction(video_id) - - # Extract the config JSON - try: - config = webpage.split(' = {config:')[1].split(',assets:')[0] - config = json.loads(config) - except: - 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): - self._verify_video_password(url, video_id, webpage) - return self._real_extract(url) - else: - raise ExtractorError(u'Unable to extract info section') - - # Extract title - video_title = config["video"]["title"] - - # Extract uploader and uploader_id - video_uploader = config["video"]["owner"]["name"] - video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None - - # Extract video thumbnail - video_thumbnail = config["video"]["thumbnail"] - - # Extract video description - video_description = get_element_by_attribute("itemprop", "description", webpage) - if video_description: video_description = clean_html(video_description) - else: video_description = u'' - - # Extract upload date - video_upload_date = None - mobj = re.search(r' 0: - video_quality = files[quality][0][2] - video_codec = files[quality][0][0] - video_extension = files[quality][0][1] - self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) - break - else: - raise ExtractorError(u'No known codec found') - - video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ - %(video_id, sig, timestamp, video_quality, video_codec.upper()) - - return [{ - 'id': video_id, - 'url': video_url, - 'uploader': video_uploader, - 'uploader_id': video_uploader_id, - 'upload_date': video_upload_date, - 'title': video_title, - 'ext': video_extension, - 'thumbnail': video_thumbnail, - 'description': video_description, - }] class ArteTvIE(InfoExtractor): diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py new file mode 100644 index 0000000000..677cf4e1c4 --- /dev/null +++ b/youtube_dl/extractor/vimeo.py @@ -0,0 +1,138 @@ +import json +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + + clean_html, + get_element_by_attribute, + ExtractorError, + std_headers, +) + +class VimeoIE(InfoExtractor): + """Information extractor for vimeo.com.""" + + # _VALID_URL matches Vimeo URLs + _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' + IE_NAME = u'vimeo' + + def _verify_video_password(self, url, video_id, webpage): + password = self._downloader.params.get('password', None) + if password is None: + raise ExtractorError(u'This video is protected by a password, use the --password option') + token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1) + data = compat_urllib_parse.urlencode({'password': password, + 'token': token}) + # I didn't manage to use the password with https + if url.startswith('https'): + pass_url = url.replace('https','http') + else: + pass_url = url + password_request = compat_urllib_request.Request(pass_url+'/password', data) + password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + password_request.add_header('Cookie', 'xsrft=%s' % token) + self._download_webpage(password_request, video_id, + u'Verifying the password', + u'Wrong password') + + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + + video_id = mobj.group('id') + if not mobj.group('proto'): + url = 'https://' + url + if mobj.group('direct_link') or mobj.group('pro'): + url = 'https://vimeo.com/' + video_id + + # Retrieve video webpage to extract further information + request = compat_urllib_request.Request(url, None, std_headers) + webpage = self._download_webpage(request, video_id) + + # Now we begin extracting as much information as we can from what we + # retrieved. First we extract the information common to all extractors, + # and latter we extract those that are Vimeo specific. + self.report_extraction(video_id) + + # Extract the config JSON + try: + config = webpage.split(' = {config:')[1].split(',assets:')[0] + config = json.loads(config) + except: + 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): + self._verify_video_password(url, video_id, webpage) + return self._real_extract(url) + else: + raise ExtractorError(u'Unable to extract info section') + + # Extract title + video_title = config["video"]["title"] + + # Extract uploader and uploader_id + video_uploader = config["video"]["owner"]["name"] + video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None + + # Extract video thumbnail + video_thumbnail = config["video"]["thumbnail"] + + # Extract video description + video_description = get_element_by_attribute("itemprop", "description", webpage) + if video_description: video_description = clean_html(video_description) + else: video_description = u'' + + # Extract upload date + video_upload_date = None + mobj = re.search(r' 0: + video_quality = files[quality][0][2] + video_codec = files[quality][0][0] + video_extension = files[quality][0][1] + self.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality)) + break + else: + raise ExtractorError(u'No known codec found') + + video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ + %(video_id, sig, timestamp, video_quality, video_codec.upper()) + + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'uploader_id': video_uploader_id, + 'upload_date': video_upload_date, + 'title': video_title, + 'ext': video_extension, + 'thumbnail': video_thumbnail, + 'description': video_description, + }]