#!/usr/bin/env python # encoding: utf-8 """ @version: ?? @author: phpergao @license: Apache Licence @file: baidu_paiming.py @time: 2016/8/1 11:10 """ import requests,re,urllib,codeop,urllib.request,nturl2path,macurl2path urllist = ["f7a2bee997ef68e8", # 丽影 "3b246a0864597e50", # 穗丰 "0ebf88697141f32f", # 冠城 "eff209d4a7f538ca", # 礼岗 "57f9e38e087acf61", # 购书 ] def chapaiming(urllist): User_Agent = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36"#伪装成浏览器访问 headers = (‘User-Agent‘, User_Agent) opener = urllib.request.build_opener() opener.addheaders = [headers] num0=1 num=1 flag=True while flag: url="http://waimai.baidu.com/waimai/shoplist/{}?display=json&page={}&count=40".format(urllist,num0) num0 += 1 ret = opener.open(url) #ret =urllib.request.urlopen(url) ret=ret.read().decode(‘unicode_escape‘) html = re.findall(r‘‘‘"shop_name":"(.*?)","shop_announcement":‘‘‘, ret) address=re.findall(r‘‘‘"poi_address":"(.*?)"},"sortby":‘‘‘,ret) for i in html: num += 1 if ‘72‘ in str(i): print(i,"排名在:{},定位地址:{}".format(num,address)) num0 = 1 flag=False break #print(i) if __name__=="__main__": for i in urllist: chapaiming(i)
原文地址:http://9272317.blog.51cto.com/9262317/1832924