def get_person_court_info(id): if id is None: return person_url = person_detail_url+id url='http://shixin.court.gov.cn/personMore.do' r = requests.get(url,headers=person_headers) cookies=r.cookies headers = { 'Accept-Encoding':'gzip, deflate,sdch', 'Accept-Language':'zh-CN,zh;q=0.8', 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.132 Safari/537.36', 'X-Requested-With':'XMLHttpRequest', 'Referer':'http://shixin.court.gov.cn/personMore.do' } return requests.get(person_url,headers=headers,cookies = cookies).text
def check_url_is_alive(self, url, cookie, data=None): result = True fail_status_codes = [404, 500] if url: headers = {'Cookie': '', 'User-Agent': self.user_agent} if cookie is None \ else {'Cookie': cookie, 'User-Agent': self.user_agent} try: req = requests.get(url, verify=True, headers=headers, timeout=5, ) if data is None \ else requests.post(url, verify=True, data=data, headers=headers, timeout=5) result = False if req.status_code in fail_status_codes else True except Exception as e: traceback.print_exc(file=open(EXCEPTION_LOG_PATH, 'a')) result = False return result
def init_req(): r=requests.get(person_court_list_url,headers=person_headers) print r.text