diff --git a/src/you_get/common.py b/src/you_get/common.py index 705c1486..9dcbb6a0 100755 --- a/src/you_get/common.py +++ b/src/you_get/common.py @@ -940,7 +940,7 @@ def script_main(script_name, download, download_playlist = None): sys.exit(1) def url_to_module(url): - from .extractors import netease, w56, acfun, baidu, baomihua, bilibili, blip, catfun, cntv, cbs, coursera, dailymotion, dongting, douban, douyutv, ehow, facebook, freesound, funshion, google, sina, ifeng, alive, instagram, iqiyi, joy, jpopsuki, khan, ku6, kugou, kuwo, letv, lizhi, magisto, metacafe, miaopai, miomio, mixcloud, mtv81, nicovideo, pptv, qianmo, qq, sohu, songtaste, soundcloud, ted, theplatform, tudou, tucao, tumblr, twitter, vid48, videobam, vidto, vimeo, vine, vk, xiami, yinyuetai, youku, youtube, zhanqi + from .extractors import netease, w56, acfun, baidu, baomihua, bilibili, blip, catfun, cntv, cbs, coursera, dailymotion, dongting, douban, douyutv, ehow, facebook, freesound, funshion, google, sina, ifeng, alive, instagram, iqiyi, joy, jpopsuki, khan, ku6, kugou, kuwo, letv, lizhi, magisto, metacafe, miaopai, miomio, mixcloud, mtv81, nicovideo, pptv, qianmo, qq, sohu, songtaste, soundcloud, ted, theplatform, tudou, tucao, tumblr, tv66wz, twitter, vid48, videobam, vidto, vimeo, vine, vk, xiami, yinyuetai, youku, youtube, zhanqi video_host = r1(r'https?://([^/]+)/', url) video_url = r1(r'https?://[^/]+(.*)', url) @@ -1007,6 +1007,7 @@ def url_to_module(url): 'tudou': tudou, 'tumblr': tumblr, 'twitter': twitter, + '66wz': tv66wz, 'vid48': vid48, 'videobam': videobam, 'vidto': vidto, diff --git a/src/you_get/extractors/__init__.py b/src/you_get/extractors/__init__.py index 2f1c268b..20d712a2 100755 --- a/src/you_get/extractors/__init__.py +++ b/src/you_get/extractors/__init__.py @@ -46,6 +46,7 @@ from .theplatform import * from .tucao import * from .tudou import * from .tumblr import * +from .tv66wz import * from .twitter import * from .vid48 import * from .videobam import * diff --git a/src/you_get/extractors/tv66wz.py b/src/you_get/extractors/tv66wz.py new file mode 100644 index 00000000..e468e39d --- /dev/null +++ b/src/you_get/extractors/tv66wz.py @@ -0,0 +1,55 @@ +#!/usr/bin/env python + +__all__ = ['tv66wz_download'] +# Attention: It is not possible to name the function as 66wz, so I've put "tv" in front of the names. + +from ..common import * +import re + +#---------------------------------------------------------------------- +def tv66wz_download(url, output_dir = '.', merge = False, info_only = False): + """str, blahblah->None + Call the API function""" + if re.match(r'http://tv.66wz.com/\w+', url): + + p = re.compile(r"g_arrVideo\[\d+\] = new videoInfo\((\d+),\d,\'(.+)\',\'") + + url_list = [] + + html = get_content(url) + + for m in p.finditer(html): + url_list.append((m.group(1), m.group(2))) + #1: id 2: title + + for i in url_list: + tv66wz_download_by_id(i[0], i[1], output_dir='.', merge=False, + info_only=False) + +#---------------------------------------------------------------------- +def tv66wz_download_by_id(id, title, output_dir = '.', merge = False, info_only = False): + """ + str,str, blahblah...-> None + Attention: title comes from previous function, arguments not exactly the same + as other extractors""" + url_httppplay = 'http://60.190.99.171:8080/forcetech/cms/flvhttpplay.jsp?id={id}&type=0&documentID=0&columnID=0'.format(id = id) + + html = get_content(url_httppplay) + + p = re.compile(r'.+filevalue=(.+)&copyvalue') + for m in p.finditer(html): + url = m.group(1) + break + + #print(url) + + print('This will take very very long...') + + type_, ext, size = url_info(url) + print_info('66wz', title, 'flv', 0) + if not info_only: + download_urls([url], title, 'flv', total_size=None, output_dir=output_dir, merge=merge) + +site_info = "66wz" +download = tv66wz_download +download_playlist = playlist_not_supported('66wz') \ No newline at end of file