Python3.5.3 爬取58同城房产数据简单例子

2019独角兽企业重金招聘Python工程师标准>>>

爬取58同城房产数据简单例子:

import requests
import re
import urllib.request
import time

#url = 'http://bj.58.com/ershoufang/?PGTID=0d200001-0000-177a-59fd-ff451a7a6078&ClickID=1'
url = 'http://jq.58.com/ershoufang/?PGTID=0d200001-0289-326f-83b1-136a8a11d60c&ClickID=1'

def get_html(url):
    r = requests.get(url)  # 最基本的GET请求
    #print(r.status_code)  # 获取返回状态
    #print(r.url)
    #print(r.text)  # 打印解码后的返回数据
    return r.text

def get_content(html):
    pattern = re.compile(r'<p class="bthead">[\s\S]*?<a href="(.*?)"  target="_blank" class="t" ')
    subUrls = pattern.findall(html)

    i = 0
    for subUrl  in subUrls:
        i += 1
        print("房产链接%d : %s" % (i, subUrl))
        #break
    return subUrls

def getHouseInfo(subUrls):
    i = 0
    for subUrl  in subUrls:
        subPage = urllib.request.urlopen(subUrl)
        subHtml = subPage.read().decode('utf8')
        i += 1
        #print(subHtml)
        #break

        # http://jq.58.com/ershoufang/29531455158954x.shtml?psid=175499680195669470620619228&entinfo=29531455158954_0
        # 售价：面议万元（元/㎡）

        #pattern = re.compile(r'售价：(\d[\d.]+)万元（(\d{1,6})元/㎡）[\s\S]*?<h1 class="c_333 f20">(.*?)</h1>[\s\S]*?<span class=\'up\' id=\'\'>(.*?)</span>[\s\S]*?<p class=\'phone-num-2\'>(\d{1,11})</p>')
        pattern = re.compile( r'售价：(.*?)万元（(.*?)元/㎡）[\s\S]*?<h1 class="c_333 f20">(.*?)</h1>[\s\S]*?<span class=\'up\' id=\'\'>(.*?)</span>[\s\S]*?<p class=\'phone-num-2\'>(\d{1,11})</p>')

        Info = pattern.findall(subHtml)
        time.sleep(0.2)
        print('%d售价:%s万元   单价:%s元/㎡   标题;%s   更新时间:%s   联系电话:%s' % (i,Info[0][0],Info[0][1],Info[0][2],Info[0][3],Info[0][4]))

html = get_html(url)
subUrls = get_content(html)
getHouseInfo(subUrls)

转载于:https://my.oschina.net/michaelshu/blog/883826