X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=9cfff153b12fce1c4db4c1420b6f0caab323a8c2;hb=95eb771dcda47f948b050da85c7ff22539e3ee12;hp=d1b239abfcd6917c14a6eba0e58cbe5f9750e1bf;hpb=59ae15a507cbf93de13f8fda8444d2d9a251747a;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d1b239abf..9cfff153b 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1,6 +1,8 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import absolute_import + import datetime import netrc import os @@ -12,7 +14,7 @@ import xml.etree.ElementTree import random import math -from utils import * +from .utils import * class InfoExtractor(object): @@ -484,8 +486,8 @@ class YoutubeIE(InfoExtractor): # Extension video_extension = self._video_extensions.get(format_param, 'flv') - video_format = '{} - {}'.format(format_param if format_param else video_extension, - self._video_dimensions.get(format_param, '???')) + video_format = '{0} - {1}'.format(format_param if format_param else video_extension, + self._video_dimensions.get(format_param, '???')) results.append({ 'id': video_id, @@ -1070,8 +1072,8 @@ class VimeoIE(InfoExtractor): self.report_extraction(video_id) # Extract the config JSON - config = webpage.split(' = {config:')[1].split(',assets:')[0] try: + config = webpage.split(' = {config:')[1].split(',assets:')[0] config = json.loads(config) except: self._downloader.trouble(u'ERROR: unable to extract info section') @@ -1669,7 +1671,7 @@ class YahooSearchIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" - _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' + _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*' _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s' _MORE_PAGES_INDICATOR = r'yt-uix-pager-next' @@ -2647,12 +2649,13 @@ class EscapistIE(InfoExtractor): class CollegeHumorIE(InfoExtractor): """Information extractor for collegehumor.com""" + _WORKING = False _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P[0-9]+)/(?P.*)$' IE_NAME = u'collegehumor' - def report_webpage(self, video_id): + def report_manifest(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + self._downloader.to_screen(u'[%s] %s: Downloading XML manifest' % (self.IE_NAME, video_id)) def report_extraction(self, video_id): """Report information extraction.""" @@ -2665,29 +2668,14 @@ class CollegeHumorIE(InfoExtractor): return video_id = mobj.group('videoid') - self.report_webpage(video_id) - request = compat_urllib_request.Request(url) - try: - webpage = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) - return - - m = re.search(r'id="video:(?P[0-9]+)"', webpage) - if m is None: - self._downloader.trouble(u'ERROR: Cannot extract internal video ID') - return - internal_video_id = m.group('internalvideoid') - info = { 'id': video_id, - 'internal_id': internal_video_id, 'uploader': None, 'upload_date': None, } self.report_extraction(video_id) - xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id + xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id try: metaXml = compat_urllib_request.urlopen(xmlUrl).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -2699,13 +2687,34 @@ class CollegeHumorIE(InfoExtractor): videoNode = mdoc.findall('./video')[0] info['description'] = videoNode.findall('./description')[0].text info['title'] = videoNode.findall('./caption')[0].text - info['url'] = videoNode.findall('./file')[0].text info['thumbnail'] = videoNode.findall('./thumbnail')[0].text - info['ext'] = info['url'].rpartition('.')[2] + manifest_url = videoNode.findall('./file')[0].text except IndexError: self._downloader.trouble(u'\nERROR: Invalid metadata XML file') return + manifest_url += '?hdcore=2.10.3' + self.report_manifest(video_id) + try: + manifestXml = compat_urllib_request.urlopen(manifest_url).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err)) + return + + adoc = xml.etree.ElementTree.fromstring(manifestXml) + try: + media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] + node_id = media_node.attrib['url'] + video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text + except IndexError as err: + self._downloader.trouble(u'\nERROR: Invalid manifest file') + return + + url_pr = compat_urllib_parse_urlparse(manifest_url) + url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1' + + info['url'] = url + info['ext'] = 'f4f' return [info] @@ -2794,13 +2803,13 @@ class SoundcloudIE(InfoExtractor): def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) - def report_webpage(self, video_id): + def report_resolve(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + self._downloader.to_screen(u'[%s] %s: Resolving id' % (self.IE_NAME, video_id)) def report_extraction(self, video_id): """Report information extraction.""" - self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + self._downloader.to_screen(u'[%s] %s: Retrieving stream' % (self.IE_NAME, video_id)) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -2809,65 +2818,47 @@ class SoundcloudIE(InfoExtractor): return # extract uploader (which is in the url) - uploader = mobj.group(1).decode('utf-8') + uploader = mobj.group(1) # extract simple title (uploader + slug of song title) - slug_title = mobj.group(2).decode('utf-8') + slug_title = mobj.group(2) simple_title = uploader + u'-' + slug_title - self.report_webpage('%s/%s' % (uploader, slug_title)) + self.report_resolve('%s/%s' % (uploader, slug_title)) - request = compat_urllib_request.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title)) + url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title) + resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28' + request = compat_urllib_request.Request(resolv_url) try: - webpage = compat_urllib_request.urlopen(request).read() + info_json_bytes = compat_urllib_request.urlopen(request).read() + info_json = info_json_bytes.decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) return + info = json.loads(info_json) + video_id = info['id'] self.report_extraction('%s/%s' % (uploader, slug_title)) - # extract uid and stream token that soundcloud hands out for access - mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage) - if mobj: - video_id = mobj.group(1) - stream_token = mobj.group(2) - - # extract unsimplified title - mobj = re.search('"title":"(.*?)",', webpage) - if mobj: - title = mobj.group(1).decode('utf-8') - else: - title = simple_title - - # construct media url (with uid/token) - mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s" - mediaURL = mediaURL % (video_id, stream_token) - - # description - description = u'No description available' - mobj = re.search('track-description-value">

(.*?)

', webpage) - if mobj: - description = mobj.group(1) - - # upload date - upload_date = None - mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)", webpage) - if mobj: - try: - upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') - except Exception as err: - self._downloader.to_stderr(compat_str(err)) + streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28' + request = compat_urllib_request.Request(streams_url) + try: + stream_json_bytes = compat_urllib_request.urlopen(request).read() + stream_json = stream_json_bytes.decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err)) + return - # for soundcloud, a request to a cross domain is required for cookies - request = compat_urllib_request.Request('http://media.soundcloud.com/crossdomain.xml', std_headers) + streams = json.loads(stream_json) + mediaURL = streams['http_mp3_128_url'] return [{ - 'id': video_id.decode('utf-8'), + 'id': info['id'], 'url': mediaURL, - 'uploader': uploader.decode('utf-8'), - 'upload_date': upload_date, - 'title': title, + 'uploader': info['user']['username'], + 'upload_date': info['created_at'], + 'title': info['title'], 'ext': u'mp3', - 'description': description.decode('utf-8') + 'description': info['description'], }]