爬取北京小猪短租网前2页信息的内容

参考网址：http://bj.xiaozhu.com/

需要爬取的信息包括：标题、地址、价格、房东名称、房东性别和房东头像的链接，将数据分别使用TXT、JSON、CSV存储。

view codeimport csv
import time
import json
import requests
from bs4 import BeautifulSoup
from requests import RequestException
    
    
def get_one_page(url):
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'}
        response = requests.get(url, headers=headers)
        #response.encoding = response.apparent_encoding
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def get_detailurl(text):
    detailurl = []
    soup = BeautifulSoup(text, 'lxml')
    result_btm_con = soup.find_all(name='div', class_='result_btm_con lodgeunitname')
    for i in range(len(result_btm_con)):
        detailurl.append(result_btm_con[i]['detailurl'])
    return detailurl
    
def parse_one_page(text):
    soup = BeautifulSoup(text, 'lxml') #使用lxml XML 解析库
    title = soup.select('.pho_info > h4 > em')
    addresse = soup.select('.pho_info > p')
    price = soup.find_all(name='span', class_='detail_avgprice')
    name = soup.find_all(name='a', class_='lorder_name')
    sex = soup.find_all(name='div', class_='member_ico')
    sex1 = soup.find_all(name='div', class_='member_ico1')
    ssex = '男' if len(sex) else '女'
    img = soup.select('.member_pic img')
    yield{ 
        'title': title[0].string,
        'address': addresse[0]['title'],
        'price': price[0].string,
        'name': name[0]['title'],
        'sex': ssex,
        'img': img[0]['src']
    }
        
def write_to_file(content):
    with open('xiaozhu.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')
        #dumps将json对象转化为字符串

def write_to_json(content):
    with open('xiaozhu.json', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+'\n')
        
def write_to_csv(content):
    with open('xiaozhu.csv', 'a', encoding='utf-8') as f:
        fieldnames = ['title','address','price','name','sex','img']
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        writer.writeheader()
        writer.writerows(content)

if __name__ == '__main__':
    url = 'http://bj.xiaozhu.com/search-duanzufang-p{}-0/'
    urls = [url.format(page) for page in range(1,3)]
    content = []
    for url in urls:
        text1 = get_one_page(url)
        detailurl = get_detailurl(text1)
        for i in detailurl:
            text2 = get_one_page(i)
            for item in parse_one_page(text2):
                print(item)
                write_to_file(item)            
                content.append(item)
    write_to_csv(content)
    write_to_json(content)