X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsohu.py;h=a62ed84f1e34b75a721914d68a101ad2a0bb8983;hb=6d874fee2a4b54272c48960f3082072d37a7e0ae;hp=83081422111ebc77927149cc2809fe10348ff793;hpb=6624a2b07dafad4de895b4e84f4595214817518d;p=youtube-dl diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 830814221..a62ed84f1 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -1,97 +1,202 @@ -# encoding: utf-8 +# coding: utf-8 +from __future__ import unicode_literals import re -import json -import time -import logging -import urllib2 from .common import InfoExtractor -from ..utils import compat_urllib_request +from ..compat import ( + compat_str, + compat_urllib_parse_urlencode, +) +from ..utils import ( + ExtractorError, + int_or_none, + try_get, +) class SohuIE(InfoExtractor): - _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P\d+)\.shtml.*?' - - _TEST = { - u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super', - u'file': u'382479172.flv', - u'md5': u'cc84eed6b6fbf0f2f9a8d3cb9da1939b', - u'info_dict': { - u'title': u'The Illest - Far East Movement Riff Raff', + _VALID_URL = r'https?://(?Pmy\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P\d+)\.shtml.*?' + + # Sohu videos give different MD5 sums on Travis CI and my machine + _TESTS = [{ + 'note': 'This video is available only in Mainland China', + 'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super', + 'info_dict': { + 'id': '382479172', + 'ext': 'mp4', + 'title': 'MV：Far East Movement《The Illest》', + }, + 'skip': 'On available in China', + }, { + 'url': 'http://tv.sohu.com/20150305/n409385080.shtml', + 'info_dict': { + 'id': '409385080', + 'ext': 'mp4', + 'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》', + } + }, { + 'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml', + 'info_dict': { + 'id': '78693464', + 'ext': 'mp4', + 'title': '【爱范品】第31期：MWC见不到的奇葩手机', + } + }, { + 'note': 'Multipart video', + 'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml', + 'info_dict': { + 'id': '78910339', + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', }, - } - - def _clearn_html(self, string): - tags = re.findall(r'<.+?>', string) - for t in tags: - string = string.replace(t, ' ') - for i in range(2): - spaces = re.findall(r'\s+', string) - for s in spaces: - string = string.replace(s, ' ') - string = string.strip() - return string + 'playlist': [{ + 'info_dict': { + 'id': '78910339_part1', + 'ext': 'mp4', + 'duration': 294, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }, { + 'info_dict': { + 'id': '78910339_part2', + 'ext': 'mp4', + 'duration': 300, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }, { + 'info_dict': { + 'id': '78910339_part3', + 'ext': 'mp4', + 'duration': 150, + 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆', + } + }] + }, { + 'note': 'Video with title containing dash', + 'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml', + 'info_dict': { + 'id': '78932792', + 'ext': 'mp4', + 'title': 'youtube-dl testing video', + }, + 'params': { + 'skip_download': True + } + }] def _real_extract(self, url): + + def _fetch_data(vid_id, mytv=False): + if mytv: + base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' + else: + base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' + + return self._download_json( + base_data_url + vid_id, video_id, + 'Downloading JSON data for %s' % vid_id, + headers=self.geo_verification_headers()) + mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + mytv = mobj.group('mytv') is not None + webpage = self._download_webpage(url, video_id) - pattern = r'

\n*?(.+?)\n*?

' - compiled = re.compile(pattern, re.DOTALL) - title = self._search_regex(compiled, webpage, u'video title').strip('\t\n') - title = self._clearn_html(title) - pattern = re.compile(r'var vid="(\d+)"') - result = re.search(pattern, webpage) - if not result: - logging.info('[Sohu] could not get vid') - return None - vid = result.group(1) - logging.info('vid: %s' % vid) - base_url_1 = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' - url_1 = base_url_1 + vid - logging.info('json url: %s' % url_1) - json_1 = json.loads(urllib2.urlopen(url_1).read()) - # get the highest definition video vid and json infomation. - vids = [] - qualities = ('oriVid', 'superVid', 'highVid', 'norVid') - for vid_name in qualities: - vids.append(json_1['data'][vid_name]) - clearest_vid = 0 - for i, v in enumerate(vids): - if v != 0: - clearest_vid = v - logging.info('quality definition: %s' % qualities[i][:-3]) - break - if not clearest_vid: - logging.warning('could not find valid clearest_vid') - return None - if vid != clearest_vid: - url_1 = '%s%d' % (base_url_1, clearest_vid) - logging.info('highest definition json url: %s' % url_1) - json_1 = json.loads(urllib2.urlopen(url_1).read()) - allot = json_1['allot'] - prot = json_1['prot'] - clipsURL = json_1['data']['clipsURL'] - su = json_1['data']['su'] - num_of_parts = json_1['data']['totalBlocks'] - logging.info('Total parts: %d' % num_of_parts) - base_url_3 = 'http://allot/?prot=prot&file=clipsURL[i]&new=su[i]' - files_info = [] - for i in range(num_of_parts): - middle_url = 'http://%s/?prot=%s&file=%s&new=%s' % (allot, prot, clipsURL[i], su[i]) - logging.info('middle url part %d: %s' % (i, middle_url)) - middle_info = urllib2.urlopen(middle_url).read().split('|') - middle_part_1 = middle_info[0] - download_url = '%s%s?key=%s' % (middle_info[0], su[i], middle_info[3]) + title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage)) + + vid = self._html_search_regex( + r'var vid ?= ?["\'](\d+)["\']', + webpage, 'video path') + vid_data = _fetch_data(vid, mytv) + if vid_data['play'] != 1: + if vid_data.get('status') == 12: + raise ExtractorError( + '%s said: There\'s something wrong in the video.' % self.IE_NAME, + expected=True) + else: + self.raise_geo_restricted( + '%s said: The video is only licensed to users in Mainland China.' % self.IE_NAME) + + formats_json = {} + for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'): + vid_id = vid_data['data'].get('%sVid' % format_id) + if not vid_id: + continue + vid_id = compat_str(vid_id) + formats_json[format_id] = vid_data if vid == vid_id else _fetch_data(vid_id, mytv) + + part_count = vid_data['data']['totalBlocks'] + + playlist = [] + for i in range(part_count): + formats = [] + for format_id, format_data in formats_json.items(): + allot = format_data['allot'] + + data = format_data['data'] + clips_url = data['clipsURL'] + su = data['su'] + + video_url = 'newflv.sohu.ccgslb.net' + cdnId = None + retries = 0 + + while 'newflv.sohu.ccgslb.net' in video_url: + params = { + 'prot': 9, + 'file': clips_url[i], + 'new': su[i], + 'prod': 'flash', + 'rb': 1, + } + + if cdnId is not None: + params['idc'] = cdnId + + download_note = 'Downloading %s video URL part %d of %d' % ( + format_id, i + 1, part_count) + + if retries > 0: + download_note += ' (retry #%d)' % retries + part_info = self._parse_json(self._download_webpage( + 'http://%s/?%s' % (allot, compat_urllib_parse_urlencode(params)), + video_id, download_note), video_id) + + video_url = part_info['url'] + cdnId = part_info.get('nid') + + retries += 1 + if retries > 5: + raise ExtractorError('Failed to get video URL') + + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'filesize': int_or_none( + try_get(data, lambda x: x['clipsBytes'][i])), + 'width': int_or_none(data.get('width')), + 'height': int_or_none(data.get('height')), + 'fps': int_or_none(data.get('fps')), + }) + self._sort_formats(formats) + + playlist.append({ + 'id': '%s_part%d' % (video_id, i + 1), + 'title': title, + 'duration': vid_data['data']['clipsDuration'][i], + 'formats': formats, + }) + + if len(playlist) == 1: + info = playlist[0] + info['id'] = video_id + else: info = { - 'id': '%s_part%02d' % (video_id, i + 1), + '_type': 'multi_video', + 'entries': playlist, + 'id': video_id, 'title': title, - 'url': download_url, - 'ext': 'mp4', } - files_info.append(info) - time.sleep(1) - return files_info + return info