证券日报网爬取实战

1 需求

证券日报网爬取贵州茅台新闻实战。

2 代码实现

import requests
import re


if __name__ == "__main__":
    # 获取网页源代码
    url = 'http://search.zqrb.cn/search.php?src=all&q=贵州茅台&f=_all&s=newsdate_DESC'
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Firefox/91.0'}
    source = requests.get(url=url, headers=headers).text
    # 获取网页标题
    p_title = ' target="_blank"><h4>(.*?)</h4></a>'
    title = re.findall(p_title, source)
    # 获取网页网址
    p_href = '.*?<a href="(.*?)" target="_blank"><h4>'
    href = re.findall(p_href, source)
    # 数据清洗
    for index in range(len(title)):
        title[index] = re.sub("<.*?>", '', title[index]).strip()
        print(str(index + 1) + "." + title[index] + "(" + href[index] + ")")
        print()