python爬取内涵吧段子标题和内容

由于内涵段子被封了,换了一个网站www.neihan8.com,利用python爬取内涵吧段子标题和内容,使用python2实现

finditer 方法

finditer 方法的行为跟 findall 的行为类似，也是搜索整个字符串，获得所有匹配的结果。但它返回一个顺序访问每一个匹配结果（Match 对象）的迭代器。

#!/usr/bin/env python
# encoding:utf-8
import re

import requests


class NeihanSpider(object):
    """内涵吧段子爬取:www.neihan8.com"""

    def __init__(self):
        self.page = 1
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5478.400 QQBrowser/10.1.1550.400 Name"
        }
        self.pattern = r'\s+
(.*?)
\s+
(.*?)
'

    def send_request(self, url, params={}):
        """发送请求"""
        print("[INFO]:正在请求<{}>".format(url))
        html = requests.get(url, params=params, headers=self.headers).content
        return html

    def save_file(self, iter):
        """保存段子"""
        with open("./段子.txt", "ab") as f:
            while True:
                try:
                    ret = next(iter)
                    title = ret.group(1)
                    content = ret.group(2)
                    # 处理掉空格
                    content = re.sub(r'　', "", content)
                    f.write(title + "\n")
                    f.write(content + "\n\n")
                except StopIteration:
                    break

    def parse_page(self, html):
        """正则处理文本"""

        # re.finditer()返回一个顺序访问每一个结果的match对象迭代器
        # 这里用finditer的原因是想要同时匹配到标题和内容
        result_iter = re.finditer(self.pattern, html)
        return result_iter

    def main(self):
        while True:
            url = "https://www.neihan8.com/article/index_" + str(self.page) + ".html"
            if self.page == 1:
                url = "https://www.neihan8.com/article/index.html"
            html = self.send_request(url)
            result_iter = self.parse_page(html)
            self.save_file(result_iter)
            print("[INFO]:第<{}>页处理完成".format(self.page))
            if raw_input("回车键继续,按q退出...") == "q":
                break
            self.page += 1


if __name__ == '__main__':
    spider = NeihanSpider()
    spider.main()

运行结果如下:

结果: