X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fletv.py;h=1484ac0d267697dceb34c9e406e3a26b26a37f54;hb=674fb0fcc54c72448f80a0573f7fd116f220827e;hp=3eb20678eda3a40d53abdadb3a6498ebf1b214ac;hpb=7f09a662a0db2ad0a338645e4f2dbd43056a6fa6;p=youtube-dl diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py index 3eb20678e..1484ac0d2 100644 --- a/youtube_dl/extractor/letv.py +++ b/youtube_dl/extractor/letv.py @@ -1,17 +1,25 @@ # coding: utf-8 from __future__ import unicode_literals -import os.path -import time import datetime +import re +import time from .common import InfoExtractor -from ..compat import (compat_urlparse, compat_urllib_parse) -from ..utils import (ExtractorError, parse_iso8601) +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, + compat_urlparse, +) +from ..utils import ( + determine_ext, + ExtractorError, + parse_iso8601, +) class LetvIE(InfoExtractor): - _VALID_URL = r'http://www.letv.com/ptv/vplay/(?P\d+).html' + _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P\d+).html' _TESTS = [{ 'url': 'http://www.letv.com/ptv/vplay/22005890.html', @@ -22,20 +30,36 @@ class LetvIE(InfoExtractor): 'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家', 'timestamp': 1424747397, 'upload_date': '20150224', + 'description': 'md5:a9cb175fd753e2962176b7beca21a47c', } }, { + 'url': 'http://www.letv.com/ptv/vplay/1415246.html', + 'info_dict': { + 'id': '1415246', + 'ext': 'mp4', + 'title': '美人天下01', + 'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda', + }, + }, { + 'note': 'This video is available only in Mainland China, thus a proxy is needed', 'url': 'http://www.letv.com/ptv/vplay/1118082.html', + 'md5': 'f80936fbe20fb2f58648e81386ff7927', 'info_dict': { 'id': '1118082', 'ext': 'mp4', - } + 'title': '与龙共舞 完整版', + 'description': 'md5:7506a5eeb1722bb9d4068f85024e3986', + }, + 'params': { + 'cn_verification_proxy': 'http://proxy.uku.im:8888' + }, }] @staticmethod def urshift(val, n): return val >> n if val >= 0 else (val + 0x100000000) >> n - # ror() and calcTimeKey() are reversed from a embedded swf file in KLetvPlayer.swf + # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf def ror(self, param1, param2): _loc3_ = 0 while _loc3_ < param2: @@ -43,7 +67,7 @@ class LetvIE(InfoExtractor): _loc3_ += 1 return param1 - def calcTimeKey(self, param1): + def calc_time_key(self, param1): _loc2_ = 773625421 _loc3_ = self.ror(param1, _loc2_ % 13) _loc3_ = _loc3_ ^ _loc2_ @@ -58,12 +82,19 @@ class LetvIE(InfoExtractor): 'platid': 1, 'splatid': 101, 'format': 1, - 'tkey': self.calcTimeKey(int(time.time())), + 'tkey': self.calc_time_key(int(time.time())), 'domain': 'www.letv.com' } + play_json_req = compat_urllib_request.Request( + 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params) + ) + cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') + if cn_verification_proxy: + play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy) + play_json = self._download_json( - 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params), - media_id, 'playJson data') + play_json_req, + media_id, 'Downloading playJson data') # Check for errors playstatus = play_json['playstatus'] @@ -99,7 +130,8 @@ class LetvIE(InfoExtractor): url_info_dict = { 'url': media_url, - 'ext': os.path.splitext(dispatch[format_id][1])[1][1:] + 'ext': determine_ext(dispatch[format_id][1]), + 'format_id': format_id, } if format_id[-1:] == 'p': @@ -108,13 +140,68 @@ class LetvIE(InfoExtractor): urls.append(url_info_dict) publish_time = parse_iso8601(self._html_search_regex( - r'发布时间 ([^<>]+) ', page, 'publish time', fatal=False), + r'发布时间 ([^<>]+) ', page, 'publish time', default=None), delimiter=' ', timezone=datetime.timedelta(hours=8)) + description = self._html_search_meta('description', page, fatal=False) return { 'id': media_id, 'formats': urls, 'title': playurl['title'], 'thumbnail': playurl['pic'], + 'description': description, 'timestamp': publish_time, } + + +class LetvTvIE(InfoExtractor): + _VALID_URL = r'http://www.letv.com/tv/(?P\d+).html' + _TESTS = [{ + 'url': 'http://www.letv.com/tv/46177.html', + 'info_dict': { + 'id': '46177', + 'title': '美人天下', + 'description': 'md5:395666ff41b44080396e59570dbac01c' + }, + 'playlist_count': 35 + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + page = self._download_webpage(url, playlist_id) + + media_urls = list(set(re.findall( + r'http://www.letv.com/ptv/vplay/\d+.html', page))) + entries = [self.url_result(media_url, ie='Letv') + for media_url in media_urls] + + title = self._html_search_meta('keywords', page, + fatal=False).split('，')[0] + description = self._html_search_meta('description', page, fatal=False) + + return self.playlist_result(entries, playlist_id, playlist_title=title, + playlist_description=description) + + +class LetvPlaylistIE(LetvTvIE): + _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P[a-z]+)/index.s?html' + _TESTS = [{ + 'url': 'http://tv.letv.com/izt/wuzetian/index.html', + 'info_dict': { + 'id': 'wuzetian', + 'title': '武媚娘传奇', + 'description': 'md5:e12499475ab3d50219e5bba00b3cb248' + }, + # This playlist contains some extra videos other than the drama itself + 'playlist_mincount': 96 + }, { + 'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml', + 'info_dict': { + 'id': 'lswjzzjc', + # The title should be "劲舞青春", but I can't find a simple way to + # determine the playlist title + 'title': '乐视午间自制剧场', + 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489' + }, + 'playlist_mincount': 7 + }]