使用xpath技术爬取段子网

from lxml import etree
import time
import json
import urllib.request
item_list = []  # 创建一个列表存储获取的信息


# 构造request对象
def handler_request(url, page):
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) Apple\
                              WebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"
    }
    get_url = url + str(page)
    request = urllib.request.Request(url=get_url, headers=headers)
    return request


# 解析获取的html文件
def parse_content(content):
    # 生成对象
    tree = etree.HTML(content)
    article_list = tree.xpath('//main[@class="col-md-8 main-content"]/article')
    # 遍历article列表
    for article in article_list:
        # 获取标题
        title = article.xpath('.//div[@class="post-head"]/h1/a/text()')[0]
        # 获取内容
        text = article.xpath('.//div[@class="post-content"]/p/text()')
        text = '\n'.join(text)  # 将内容进行拼接
        item = {
            '标题': title,
            '内容': text,
        }
        item_list.append(item)


def main():
    start_page = int(input("请输入查询起始页面:"))
    end_page = int(input("查询结束页面:"))
    url = "http://duanziwang.com/page/"
    for page in range(start_page, end_page+1):
        request = handler_request(url, page)
        try:
            content = urllib.request.urlopen(request).read().decode()
            parse_content(content)
        except:
            print("第%d页面爬取失败" % page)
    string = json.dumps(item_list, ensure_ascii=False)
    with open('duanzi.txt', "w", encoding='utf-8') as f:
        f.write(string)


if __name__ == '__main__':
    main()

 

猜你喜欢

转载自www.cnblogs.com/nxrs/p/11365422.html
0条评论
添加一条新回复
  
今日推荐