2012-08-20 19:54:03 +04:00
|
|
|
#!/usr/bin/env python3
|
|
|
|
|
|
|
|
|
|
__all__ = ['tudou_download', 'tudou_download_playlist', 'tudou_download_by_id', 'tudou_download_by_iid']
|
|
|
|
|
|
|
|
|
|
from common import *
|
|
|
|
|
|
|
|
|
|
def tudou_download_by_iid(iid, title, output_dir = '.', merge = True, info_only = False):
|
|
|
|
|
xml = get_html('http://v2.tudou.com/v?it=' + iid + '&st=1,2,3,4,99')
|
|
|
|
|
|
|
|
|
|
from xml.dom.minidom import parseString
|
|
|
|
|
doc = parseString(xml)
|
|
|
|
|
title = title or doc.firstChild.getAttribute('tt') or doc.firstChild.getAttribute('title')
|
|
|
|
|
urls = [(int(n.getAttribute('brt')), n.firstChild.nodeValue.strip()) for n in doc.getElementsByTagName('f')]
|
|
|
|
|
|
|
|
|
|
url = max(urls, key = lambda x:x[0])[1]
|
|
|
|
|
assert 'f4v' in url
|
|
|
|
|
|
|
|
|
|
type, ext, size = url_info(url)
|
|
|
|
|
|
|
|
|
|
print_info(site_info, title, type, size)
|
|
|
|
|
if not info_only:
|
|
|
|
|
#url_save(url, filepath, bar):
|
|
|
|
|
download_urls([url], title, ext, total_size = None, output_dir = output_dir, merge = merge)
|
|
|
|
|
|
|
|
|
|
def tudou_download_by_id(id, title, output_dir = '.', merge = True):
|
|
|
|
|
html = get_html('http://www.tudou.com/programs/view/%s/' % id)
|
|
|
|
|
iid = r1(r'iid\s*=\s*(\S+)', html)
|
|
|
|
|
tudou_download_by_iid(iid, title, output_dir = output_dir, merge = merge)
|
|
|
|
|
|
|
|
|
|
def tudou_download(url, output_dir = '.', merge = True, info_only = False):
|
|
|
|
|
html = get_decoded_html(url)
|
|
|
|
|
iid = r1(r'iid\s*[:=]\s*(\d+)', html)
|
|
|
|
|
assert iid
|
|
|
|
|
title = r1(r'kw\s*[:=]\s*"([^"]+)"', html)
|
|
|
|
|
assert title
|
|
|
|
|
title = unescape_html(title)
|
|
|
|
|
tudou_download_by_iid(iid, title, output_dir = output_dir, merge = merge, info_only = info_only)
|
|
|
|
|
|
|
|
|
|
def parse_playlist(url):
|
|
|
|
|
#if r1('http://www.tudou.com/playlist/p/a(\d+)\.html', url):
|
|
|
|
|
# html = get_html(url)
|
|
|
|
|
# print re.search(r'<script>var.*?</script>', html, flags=re.S).group()
|
|
|
|
|
#else:
|
|
|
|
|
# raise NotImplementedError(url)
|
|
|
|
|
raise NotImplementedError()
|
|
|
|
|
|
|
|
|
|
def parse_playlist(url):
|
|
|
|
|
aid = r1('http://www.tudou.com/playlist/p/a(\d+)(?:i\d+)?\.html', url)
|
|
|
|
|
html = get_decoded_html(url)
|
|
|
|
|
if not aid:
|
|
|
|
|
aid = r1(r"aid\s*[:=]\s*'(\d+)'", html)
|
|
|
|
|
if re.match(r'http://www.tudou.com/albumcover/', url):
|
|
|
|
|
atitle = r1(r"title\s*:\s*'([^']+)'", html)
|
|
|
|
|
elif re.match(r'http://www.tudou.com/playlist/p/', url):
|
|
|
|
|
atitle = r1(r'atitle\s*=\s*"([^"]+)"', html)
|
|
|
|
|
else:
|
|
|
|
|
raise NotImplementedError(url)
|
|
|
|
|
assert aid
|
|
|
|
|
assert atitle
|
|
|
|
|
import json
|
|
|
|
|
#url = 'http://www.tudou.com/playlist/service/getZyAlbumItems.html?aid='+aid
|
|
|
|
|
url = 'http://www.tudou.com/playlist/service/getAlbumItems.html?aid='+aid
|
|
|
|
|
return [(atitle + '-' + x['title'], str(x['itemId'])) for x in json.loads(get_html(url))['message']]
|
|
|
|
|
|
2012-08-31 02:19:22 +04:00
|
|
|
def tudou_download_playlist(url, output_dir = '.', merge = True, info_only = False):
|
2012-08-20 19:54:03 +04:00
|
|
|
videos = parse_playlist(url)
|
|
|
|
|
for i, (title, id) in enumerate(videos):
|
|
|
|
|
print('Downloading %s of %s videos...' % (i + 1, len(videos)))
|
2012-08-31 02:19:22 +04:00
|
|
|
tudou_download_by_iid(id, title, output_dir = output_dir, merge = merge, info_only = info_only)
|
2012-08-20 19:54:03 +04:00
|
|
|
|
|
|
|
|
site_info = "Tudou.com"
|
|
|
|
|
download = tudou_download
|
|
|
|
|
download_playlist = tudou_download_playlist
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
main('tudou', tudou_download, tudou_download_playlist)
|
