def scan_list(self, target, exists):
list = []
result_list = []
cap = 'data'
ruler = 'author:author;title:title;date:posttime;img:picurl;link:url;top:top;click:readnum_newest;vote_up:likenum_newest;subject:content'
url = self.url.format(target.extra0, target.wx_hao)
header = {'X-Requested-With': 'XMLHttpRequest'}
raw = RequestHelper.get(url, header=header, file_cookie=Configs.gsdata_cookie_file)
try:
self.looper_js(list, raw, exists, ruler, cap)
except Exception as e:
E.out_err(e)
return (-1, (target, None, None, None))
if len(list) > 0:
list = self.sort(list)
list.reverse()
for item in list:
if exists.count(item['title']) < 1:
result_list.append(item)
LogGo.debug('newrank list length:' + str(len(result_list)))
if len(result_list) > 0:
return (1, (target, list, None, None))
return(-1, (target, None, None, None))
def scan(self, target, order):
result = []
type = self.td(target)
url = target.extra0 #'http://ent.people.com.cn/GB/81374/index1.html'
cap = None
ruler = None
if self.td(target) == 'i':
cap = ['var tvInfoJs=', '']
url = self.iqiyi_base.format(url)
ruler = 'keywords:contentKeyword;latestOrder:latestOrder;name:name;playCount:playCount;score:score;videoCount:videoCount'
elif type == 'l':
ruler = 'score:plist_score;comments:pcommon_count;bullets:pdm_count;like:up;hate:down;playCount:plist_play_count'
url = self.letv_base.format(url, target.extra1)
elif type == 't':
cap = ["tlux.dispatch('$cover',", ");"]
ruler = 'score:score->score;playCount:view_all_count;videoCount:episode_all;latestOrder:episode_updatedd'
url = self.qq_base.format(url)
elif type == 'm':
url = self.mgtv_base.format(url)
cap = ['"data":', ',"msg"']
ruler = 'playCount:all;like:like;hate:unlike'
elif type == 'y':
ruler = 'playCount:li [总播放数];comments:li [评论];like:li [顶];score:span class=star-num'
if not s.is_url(url):
if not url.startswith('id'):
url = self.youku_prefix.format(url)
url = self.youku_base.format(url)
elif type == 's':
url = self.sohu_base.format(url)
elif type == 'c':
url = self.cntv_base.format(url)
ruler = 'playCount:^label [播放次数]'
try:
encode = ExtraHtml.get_page_encode(url)
if type == 'y' or type == 'c':
result = self.looper_html(url, ruler, encode, target)
else:
raw = RequestHelper.get(url, encode=encode)
if type == 's':
result = self.finder_sohu(raw)
else:
result = self.looper_js(raw, ruler, cap)
except AttributeError as e:
pass
except Exception as e:
import traceback
msg = traceback.format_exc()
print(msg)
LogGo.warning(repr(e))
if len(result) > 0:
result = self.build_base_dic(target, result, order)
return result[0]
def get_request():
url = 'http://app.media-plus.cn/portal/search/updateIndex'
RequestHelper.get(url)