python抓取贝壳房源信息 - 耀扬

python抓取贝壳房源信息

分析了贝壳的房源信息数据，发现地址链接的参数传递是有规律的

https://tj.ke.com/chengjiao/a3l4/

a3 实际表示的 

l4 表示的是

 

 然后 将复合条件拼成一个字符串，带过去。看着真的很像加密过的。赞

import os, re
import requests
import random
import time
from bs4 import BeautifulSoup

user_agent_list = [
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
    "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]
UA = random.choice(user_agent_list)  ##从self.user_agent_list中随机取出一个字符串
headers = {\'User-Agent\': UA}  ##构造成一个完整的User-Agent （UA代表的是上面随机取出来的字符串哦）

url = \'https://tj.ke.com/chengjiao/pg\'

for x in range(2,41):

    time.sleep(random.randint(2,5))

    with requests.get(url+str(x)+\'ddo22p7\', headers=headers, timeout=5) as response:

        soup = BeautifulSoup(response.text, \'lxml\')

        # print(soup.title.text)  # 打印title

        li_list = soup.find(\'ul\', class_=\'listContent\').find_all(\'li\')
        # print(li_list)
        for li_quick in li_list:

            try:
                #取成交日期
                dealDate=li_quick.find(\'div\',class_=\'dealDate\').get_text().strip()
                #取名称
                title=li_quick.find(\'div\',class_=\'title\').a.get_text().strip()
                #取总价
                totalPrice=li_quick.find(\'div\',class_=\'totalPrice\').find(\'span\',class_=\'number\').get_text().strip()
                #取单价
                unitPrice=li_quick.find(\'div\',class_=\'unitPrice\').find(\'span\',class_=\'number\').get_text().strip()
                #取位置信息
                positionInfo=li_quick.find(\'div\',class_=\'positionInfo\').get_text().strip()
                #取成交周期
                dealCycleTxt0=li_quick.find(\'div\',class_=\'dealCycleeInfo\').find(\'span\',class_=\'dealCycleTxt\').find_all(\'span\')[0].get_text().strip()
                #取挂牌价格
                dealCycleTxt1=li_quick.find(\'div\',class_=\'dealCycleeInfo\').find(\'span\',class_=\'dealCycleTxt\').find_all(\'span\')[1].get_text().strip()
            except:
                continue
            finally:
                print(title,\',\',dealDate,\',\',totalPrice,\',\',unitPrice,\',\',dealCycleTxt0,\',\',dealCycleTxt1,\',\',positionInfo)