# coding: utf-8
from __future__ import unicode_literals
-import itertools
import random
import re
import string
from .common import InfoExtractor
from ..utils import (
ExtractorError,
- get_element_by_attribute,
+ get_element_by_class,
+ js_to_json,
+ str_or_none,
+ strip_jsonp,
)
IE_DESC = '优酷'
_VALID_URL = r'''(?x)
(?:
- http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+ https?://(
+ (?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+ video\.tudou\.com/v/)|
youku:)
(?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
'''
'id': 'XMTc1ODE5Njcy',
'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
'ext': 'mp4',
+ 'duration': 74.73,
+ 'thumbnail': r're:^https?://.*',
+ 'uploader': '。躲猫猫、',
+ 'uploader_id': '36017967',
+ 'uploader_url': 'http://i.youku.com/u/UMTQ0MDcxODY4',
+ 'tags': list,
}
}, {
'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
'id': 'XODgxNjg1Mzk2',
'ext': 'mp4',
'title': '武媚娘传奇 85',
+ 'duration': 1999.61,
+ 'thumbnail': r're:^https?://.*',
+ 'uploader': '疯狂豆花',
+ 'uploader_id': '62583473',
+ 'uploader_url': 'http://i.youku.com/u/UMjUwMzMzODky',
+ 'tags': list,
},
}, {
'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
'id': 'XMTI1OTczNDM5Mg',
'ext': 'mp4',
'title': '花千骨 04',
+ 'duration': 2363,
+ 'thumbnail': r're:^https?://.*',
+ 'uploader': '放剧场-花千骨',
+ 'uploader_id': '772849359',
+ 'uploader_url': 'http://i.youku.com/u/UMzA5MTM5NzQzNg==',
+ 'tags': list,
},
}, {
'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
'id': 'XNjA1NzA2Njgw',
'ext': 'mp4',
'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
+ 'duration': 7264.5,
+ 'thumbnail': r're:^https?://.*',
+ 'uploader': 'FoxJin1006',
+ 'uploader_id': '322014285',
+ 'uploader_url': 'http://i.youku.com/u/UMTI4ODA1NzE0MA==',
+ 'tags': list,
},
'params': {
'videopassword': '100600',
'id': 'XOTUxMzg4NDMy',
'ext': 'mp4',
'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
+ 'duration': 702.08,
+ 'thumbnail': r're:^https?://.*',
+ 'uploader': '明月庄主moon',
+ 'uploader_id': '38465621',
+ 'uploader_url': 'http://i.youku.com/u/UMTUzODYyNDg0',
+ 'tags': list,
},
+ }, {
+ 'url': 'http://video.tudou.com/v/XMjIyNzAzMTQ4NA==.html?f=46177805',
+ 'info_dict': {
+ 'id': 'XMjIyNzAzMTQ4NA',
+ 'ext': 'mp4',
+ 'title': '卡马乔国足开大脚长传冲吊集锦',
+ 'duration': 289,
+ 'thumbnail': r're:^https?://.*',
+ 'uploader': '阿卜杜拉之星',
+ 'uploader_id': '2382249',
+ 'uploader_url': 'http://i.youku.com/u/UOTUyODk5Ng==',
+ 'tags': list,
+ },
+ }, {
+ 'url': 'http://video.tudou.com/v/XMjE4ODI3OTg2MA==.html',
+ 'only_matching': True,
}]
@staticmethod
# request basic data
basic_data_params = {
'vid': video_id,
- 'ccode': '0401',
+ 'ccode': '0590',
'client_ip': '192.168.1.1',
'utid': cna,
'client_ts': time.time() / 1000,
raise ExtractorError(msg)
# get video title
- title = data['video']['title']
+ video_data = data['video']
+ title = video_data['title']
formats = [{
'url': stream['m3u8_url'],
'id': video_id,
'title': title,
'formats': formats,
+ 'duration': video_data.get('seconds'),
+ 'thumbnail': video_data.get('logo'),
+ 'uploader': video_data.get('username'),
+ 'uploader_id': str_or_none(video_data.get('userid')),
+ 'uploader_url': data.get('uploader', {}).get('homepage'),
+ 'tags': video_data.get('tags'),
}
class YoukuShowIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?youku\.com/show_page/id_(?P<id>[0-9a-z]+)\.html'
+ _VALID_URL = r'https?://list\.youku\.com/show/id_(?P<id>[0-9a-z]+)\.html'
IE_NAME = 'youku:show'
- _TEST = {
- 'url': 'http://www.youku.com/show_page/id_zc7c670be07ff11e48b3f.html',
+ _TESTS = [{
+ 'url': 'http://list.youku.com/show/id_zc7c670be07ff11e48b3f.html',
'info_dict': {
'id': 'zc7c670be07ff11e48b3f',
- 'title': '花千骨 未删减版',
- 'description': 'md5:578d4f2145ae3f9128d9d4d863312910',
+ 'title': '花千骨 DVD版',
+ 'description': 'md5:a1ae6f5618571bbeb5c9821f9c81b558',
},
'playlist_count': 50,
- }
-
- _PAGE_SIZE = 40
+ }, {
+ # Episode number not starting from 1
+ 'url': 'http://list.youku.com/show/id_zefbfbd70efbfbd780bef.html',
+ 'info_dict': {
+ 'id': 'zefbfbd70efbfbd780bef',
+ 'title': '超级飞侠3',
+ 'description': 'md5:275715156abebe5ccc2a1992e9d56b98',
+ },
+ 'playlist_count': 24,
+ }, {
+ # Ongoing playlist. The initial page is the last one
+ 'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
+ 'only_matching': True,
+ }, {
+ # No data-id value.
+ 'url': 'http://list.youku.com/show/id_zefbfbd61237fefbfbdef.html',
+ 'only_matching': True,
+ }, {
+ # Wrong number of reload_id.
+ 'url': 'http://list.youku.com/show/id_z20eb4acaf5c211e3b2ad.html',
+ 'only_matching': True,
+ }]
- def _find_videos_in_page(self, webpage):
- videos = re.findall(
- r'<li><a[^>]+href="(?P<url>https?://v\.youku\.com/[^"]+)"[^>]+title="(?P<title>[^"]+)"', webpage)
- return [
- self.url_result(video_url, YoukuIE.ie_key(), title)
- for video_url, title in videos]
+ def _extract_entries(self, playlist_data_url, show_id, note, query):
+ query['callback'] = 'cb'
+ playlist_data = self._download_json(
+ playlist_data_url, show_id, query=query, note=note,
+ transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html')
+ if playlist_data is None:
+ return [None, None]
+ drama_list = (get_element_by_class('p-drama-grid', playlist_data)
+ or get_element_by_class('p-drama-half-row', playlist_data))
+ if drama_list is None:
+ raise ExtractorError('No episodes found')
+ video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)
+ return playlist_data, [
+ self.url_result(self._proto_relative_url(video_url, 'http:'), YoukuIE.ie_key())
+ for video_url in video_urls]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
- entries = self._find_videos_in_page(webpage)
-
- playlist_title = self._html_search_regex(
- r'<span[^>]+class="name">([^<]+)</span>', webpage, 'playlist title', fatal=False)
- detail_div = get_element_by_attribute('class', 'detail', webpage) or ''
- playlist_description = self._html_search_regex(
- r'<span[^>]+style="display:none"[^>]*>([^<]+)</span>',
- detail_div, 'playlist description', fatal=False)
-
- for idx in itertools.count(1):
- episodes_page = self._download_webpage(
- 'http://www.youku.com/show_episode/id_%s.html' % show_id,
- show_id, query={'divid': 'reload_%d' % (idx * self._PAGE_SIZE + 1)},
- note='Downloading episodes page %d' % idx)
- new_entries = self._find_videos_in_page(episodes_page)
- entries.extend(new_entries)
- if len(new_entries) < self._PAGE_SIZE:
- break
-
- return self.playlist_result(entries, show_id, playlist_title, playlist_description)
+ entries = []
+ page_config = self._parse_json(self._search_regex(
+ r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'),
+ show_id, transform_source=js_to_json)
+ first_page, initial_entries = self._extract_entries(
+ 'http://list.youku.com/show/module', show_id,
+ note='Downloading initial playlist data page',
+ query={
+ 'id': page_config['showid'],
+ 'tab': 'showInfo',
+ })
+ first_page_reload_id = self._html_search_regex(
+ r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id')
+ # The first reload_id has the same items as first_page
+ reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)
+ entries.extend(initial_entries)
+ for idx, reload_id in enumerate(reload_ids):
+ if reload_id == first_page_reload_id:
+ continue
+ _, new_entries = self._extract_entries(
+ 'http://list.youku.com/show/episode', show_id,
+ note='Downloading playlist data page %d' % (idx + 1),
+ query={
+ 'id': page_config['showid'],
+ 'stage': reload_id,
+ })
+ if new_entries is not None:
+ entries.extend(new_entries)
+ desc = self._html_search_meta('description', webpage, fatal=False)
+ playlist_title = desc.split(',')[0] if desc else None
+ detail_li = get_element_by_class('p-intro', webpage)
+ playlist_description = get_element_by_class(
+ 'intro-more', detail_li) if detail_li else None
+
+ return self.playlist_result(
+ entries, show_id, playlist_title, playlist_description)
projects / youtube-dl / blobdiff