Requests，BeautifulSoup实战之房天下信息获取

import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
ua = UserAgent()
"""
headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
           }
"""
def Get_Informatica(url):
    headers = {
        'User-Agent': ua.random,#随机获取headers
    }
    data = requests.get(url, headers=headers)
    #第一页：http://zu.fang.com/house/a210-n31/  或者http://zu.fang.com/house/a210-i31-n31/
    # 第二页：http://zu.fang.com/house/a210-i32-n31/
    # 第三页：http://zu.fang.com/house/a210-i33-n31/
    # print(data.text)
    data.encoding = "gbk"
    soup = BeautifulSoup(data.text, 'lxml')
    contents = soup.find_all('dl', class_='list hiddenMap rel')
    for content in contents:
        Data_dict = {
            "title": content.find('p', class_="title").text.strip(),
            "Introduction": content.find('p', class_="font15 mt12 bold").text.strip(),
            "price": content.find('span', class_="price").text.strip(),
            "Address":content.find('p', class_="gray6 mt12").text.strip()
        }
        print(Data_dict)
        Save_file(Data_dict)
def Save_file(data):
    with open(r"C:\Users\wf\Desktop\爬虫介绍\Fangtianxia.txt",'a') as f:
        f.write(str(data)+ '\n')
if __name__ == '__main__':
    total_page = 3
    pre_url = "http://zu.fang.com/house/a210-i3"
    end_url = "-n31/"
    for page_num in range(total_page):
        url = pre_url + str(page_num+1) + end_url
        print(url)
        Get_Informatica(url)