def tudou_download(url, vidfmt):
http = HttpUtil()
html = http.get(url)
charset = http.parse_charset()
html = html.decode(charset)
iid = r1(r'"k":([^,]*),', html)
if not iid:
iid = r1(r'iid\s*[:=]\s*(\d+)', html)
assert iid
title = r1(r"kw\s*[:=]\s*['\"]([^']+)['\"]", html)
assert title
title = unescape_html(title)
return tudou_download_by_iid(iid, title)
def tudou_download_by_iid(iid, title):
url = r'http://v2.tudou.com/f?id=' + iid + r'&sid=11000&hd=2&sj=1&areaCode=110000'
xml = HttpUtil().get(url)
xml = unescape_html(xml)
url = BeautifulSoup(xml).find('f').text
return [url], title, 'flv', 1, headers