python3 爬虫之爬取安居客二手房资讯(第一版)

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Author;Tsukasa



import requests
from bs4 import BeautifulSoup
import pandas
import time


url_all = []
url_in = input('输入你所需要城市的字母简写:\n如:中山 zs , 广州 gz\n!!!不要乱输入,不然运行不了')
url_number = 1+int(input('输入爬取页数:'))

okl = []
def open(nobe):
    res = requests.get(nobe)
    soup = BeautifulSoup(res.text,'html5lib')
    http_start = []
    url_start = 'http://esf.'+url_in+'.fang.com'
    for title in soup.select('.houseList dl'):  #网址链接列表
        url_end = title.select('.title a ')[0]['href']
        http_start.append(url_start + url_end)
    return http_start


#获取详细信息
def content(url):
    info = {}
    info['网页'] = url
    res = requests.get(url)
    soup = BeautifulSoup(res.text,'html5lib')
    info['标题'] = soup.select('h1')[0].text.strip()  #获取标题
    info['总价'] = soup.select('.red20b')[0].text + '万'   #总价
    info['联系电话'] = soup.select('#mobilecode')[0].text   #电话
    for sl in soup.select('span'):  #获取发布时间
        if '发布时间' in sl.text.lstrip('<span>'):
            key , value = (sl.text.strip().rstrip('(').split(':'))
            info[key] = value + '*' + soup.select('#Time')[0].text
    for dd in soup.select('dd'):  #获取详细内容
        if ':' in dd.text.strip():
            key , value = (dd.text.strip().split(':'))
            info[key] = value
    return info




print('----------正在运行,请不要关闭----------')
url_home = ('http://esf.'+ url_in + '.fang.com/house/i3{}/')
for url_next in range(1,url_number):
    url_all.append((url_home.format(url_next)))

home = []
for i in url_all:
    a = (open(i))
    print('正在获取 -----> ',i,' <-----')
    time.sleep(1)
    for b in a:
        home.append(content(b))
        print('\t正在获取详细信息 -> ',b,' <-----')
        time.sleep(2)

    #home.append(content(open(i[0])))
last = pandas.DataFrame(home)
last.to_excel('temp.xlsx',sheet_name='房源信息')
print('----------运行结束----------\n\n----------查看根目录---------')


abcdefg = input('完成运行')

  源码先奉上,以后在填坑

posted @ 2017-04-17 00:27  Tsukasa鱼  阅读(3415)  评论(3编辑  收藏  举报