利用bs4获取58同城城市分类,bs4获取58同城,bs4的一些基本操作练手


bs4的一些基本操作练手,获取58同城合租页面下的城市分类信息

# -*- coding:utf-8 -*-#! /usr/bin/pythonimport urllibimport os, datetime, sysfrom bs4 import BeautifulSoupreload(sys) sys.setdefaultencoding( "utf-8" ) __BASEURL__ = "<a href="http://bj.58.com/">http://bj.58.com/"__INITURL__ = "<a href="http://bj.58.com/hezu/">http://bj.58.com/hezu/"soup=BeautifulSoup(urllib.urlopen(__INITURL__))lv1Elements = soup.html.body.section.find('div', 'relative').find('dl', 'secitem')('a',href=True)f=open('data.txt', 'w')for element in lv1Elements[1:]:    f.write((element.get_text() + '\\r\\n'))    print element.get_text()    url = __BASEURL__ + element.get('href')    print url    soup=BeautifulSoup(urllib.urlopen(url))    lv2Elements = soup.html.body.section.find('div', 'relative').find('dl', 'secitem').find('div', 'subarea').find_all('a')    texts = [t.get_text() for t in lv2Elements]    f.write(' '.join(texts) + '\\r\\n\\r\\n')f.close()#该片段来自于http://byrx.net

评论关闭