使用python BeautifulSoup库抓取58手机维修信息

342次阅读  |  发布于5年以前

直接上代码:

复制代码 代码如下:

!/usr/bin/python

-- coding: utf-8 --

import urllib

import os,datetime,string

import sys

from bs4 import BeautifulSoup

reload(sys)

sys.setdefaultencoding('utf-8')

BASEURL = 'http://bj.58.com/'

INITURL = "http://bj.58.com/shoujiweixiu/"

soup = BeautifulSoup(urllib.urlopen(INITURL))

lvlELements = soup.html.body.find('div','selectbarTable').find('tr').find_next_sibling('tr')('a',href=True)

f = open('data1.txt','a')

for element in lvlELements[1:]:

f.write((element.get_text()+'\n\r' ))

url = __BASEURL__ + element.get('href')

print url

soup = BeautifulSoup(urllib.urlopen(url))

lv2ELements = soup.html.body.find('table','tblist').find_all('tr')

for item in lv2ELements:  
    addr = item.find('td','t').find('a').get_text()  
    phone = item.find('td','tdl').find('b','tele').get_text()  
    f.write('地址:'+addr +' 电话:'+ phone + '\r\n\r')

f.close()

Copyright© 2013-2020

All Rights Reserved 京ICP备2023019179号-8