python爬虫示例

import urllib.parse
import urllib.request
from lxml import etree


# 定制对象
def create_request(page):
   
    url = '你的url-2.html'
    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
    }
    request = urllib.request.Request(url=url, headers=header)
    return request


# 获取内容
def get_contend(request):
    # 获取handler对象
    handler = urllib.request.HTTPHandler()
    # 获取opener对象
    opener = urllib.request.build_opener(handler)
    # 调用open方法
    reponse = opener.open(request)
    contends = reponse.read().decode('utf-8')
    return contends


# 下载
def down_load_file(contend):
    tree = etree.HTML(contend)
    # names = tree.xpath('//div[@class="item"]//img/@alt')
    srcs = tree.xpath('//ignore_js_op/img/@zoomfile')
    filename = 'C:\\Users\\nk\\code\\py\\pythonProject\\pachong\\pachongphoto\\'
    for i in range(len(srcs)):
        print(srcs[i])
        name = "q" + str(i)
        src = srcs[i]
        url = "https://www.jvidme.com/" + src
        urllib.request.urlretrieve(url, filename=filename + name + '.jpg')


if __name__ == '__main__':
    start = int(input("起始页码"))
    end = int(input("结束的页码"))
    # for page in range(start, end + 1):
    request = create_request(0)
    contends = get_contend(request)
    down_load_file(contends)