import csv import requests from lxml import etree if __name__ == "__main__": url = 'https://jn.lianjia.com/zufang/pg{}' header = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36 Edg/113.0.1774.57' } # 爬取源码数据 headers = ["区域", "小区名称", "户型", "面积(㎡)", "价格(元/月)"] path = "链家济南租房数据.csv" with open(path, 'w', newline='') as f: csv_write = csv.writer(f) csv_head = ["区域", "小区名称", "户型", "面积(㎡)", "价格(元/月)"] csv_write.writerow(csv_head) for num in range: new_url = url.format(num) page_num1 = requests.get(url=new_url, headers=header) page_num1.encoding = ('utf-8') page_num = page_num1.text tree = etree.HTML(page_num) # 存储的就是标签对象 div_list = tree.xpath('//*[@id="content"]/div[1]/div[1]/div') with open(path, 'a', newline='') as f: csv_write = csv.writer(f) for div in div_list: quyu = div.xpath('./div/p[2]/a[1]//text()')[0] name = div.xpath('./div/p[2]/a[3]//text()')[0] area = div.xpath('./div/p[2]/text()')[4].split()[0] type = div.xpath('./div/p[2]/text()')[6].split()[0] place = div.xpath('./div//span/em/text()')[0] data_row = [quyu, name, type, area, place] csv_write.writerow(data_row) print("完成")改成获取全部信息

好的，针对您的需求，可以将代码修改如下：

import csv 
import requests 
from lxml import etree 

if __name__ == "__main__":
    url = 'https://jn.lianjia.com/zufang/pg{}' 
    header = { 
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36 Edg/113.0.1774.57' 
    } 
    
    # 爬取源码数据 
    headers = ["区域", "小区名称", "户型", "面积(㎡)", "价格(元/月)"] 
    path = "链家济南租房数据.csv" 
    with open(path, 'w', newline='') as f: 
        csv_write = csv.writer(f) 
        csv_head = ["区域", "小区名称", "户型", "面积(㎡)", "价格(元/月)"] 
        csv_write.writerow(csv_head) 

    # 获取总页数
    first_page = requests.get(url.format(1), headers=header) 
    first_page.encoding = ('utf-8') 
    first_tree = etree.HTML(first_page.text) 
    total_page = int(first_tree.xpath('//*[@id="content"]/div[1]/div[2]/div/a[last()-1]/text()')[0]) 

    # 爬取每一页的数据
    with open(path, 'a', newline='') as f: 
        csv_write = csv.writer(f) 
        for num in range(1, total_page+1): 
            new_url = url.format(num) 
            page_num1 = requests.get(url=new_url, headers=header) 
            page_num1.encoding = ('utf-8') 
            page_num = page_num1.text 
            tree = etree.HTML(page_num) 

            # 存储的就是标签对象 
            div_list = tree.xpath('//*[@id="content"]/div[1]/div[1]/div') 

            for div in div_list: 
                quyu = div.xpath('./div/p[2]/a[1]//text()')[0] 
                name = div.xpath('./div/p[2]/a[3]//text()')[0] 
                area = div.xpath('./div/p[2]/text()')[4].split()[0] 
                type = div.xpath('./div/p[2]/text()')[6].split()[0] 
                place = div.xpath('./div//span/em/text()')[0] 
                data_row = [quyu, name, type, area, place] 
                csv_write.writerow(data_row) 
            print("第{}页完成".format(num))
    print("所有数据爬取完成")

这样，代码就可以自动获取总页数，然后遍历每一页获取数据。在输出的时候，也会打印出当前爬取的页数，方便查看进度。