1. import requests
    2. from lxml import etree
    3. import csv
    5. def read_page(url, headers):
    6.     data_list = []
    7.     res1 = requests.get(url, headers=headers)
    8.     html1 = etree.HTML(res1.text)
    9.     div_tags = html1.xpath('//div[@id="main"]/div/div')
    10.     for div_tag in div_tags:
    11.         item = {}
    12.         url2 = "https:"+div_tag.xpath('./a/@href')[0]
    13.         res2 = requests.get(url2, headers=headers)
    14.         html2 = etree.HTML(res2.text)
    15.         item['url'] = html2.xpath('//ul[@class="clearfix"]/li[1]/a/@href')[0]
    16.         item['name'] = div_tag.xpath('./p/a/text()')[0].replace('免费下载', '')
    17.         data_list.append(item)
    18.     return data_list
    20. def write(dig):
    21.     with open('jianlimuban.csv', 'w', encoding='utf-8-sig', newline='') as f:
    22.         wt = csv.DictWriter(f, fieldnames=['url', 'name'])
    23.         wt.writeheader()
    24.         wt.writerows(data_list)
    26. headers = {
    27. 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36'
    28. }
    29. for i in range(1, 6):
    30.     url = f'https://aspx.sc.chinaz.com/query.aspx?keyword=%E5%85%8D%E8%B4%B9&issale=&classID=864&page={i}'
    31.     data_list = read_page(url, headers)
    32.     write(data_list)