用python爬虫爬取知乎热榜

今天药忘吃喽~ 2021-07-27 00:57 635阅读 0赞

## 用python爬虫爬取知乎热榜 ##

**话不多说，直接上代码！**

import requests
    import re
    from lxml import etree
    
    content_re = re.compile('"excerptArea":{"text":"(.*?)"}')
    url_re = re.compile('"link":{"url":"(.*?)"')
    
    headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36 Edg/84.0.522.59"}
    
    def get_hot(url):
        html = requests.get(url,headers=headers)
        soup = etree.HTML(html.text)
        hots = soup.xpath('//a[@class="HotList-item"]')
        for h in hots:
            title = "标题："+h.xpath('div/div[@class="HotList-itemTitle"]/text()')[0]+'\n'
            with open("C:/Users/86135/Desktop/知乎热榜.txt",'at') as f:
                f.write(title)
        images = soup.xpath('//div[@class="HotList-itemImgContainer"]/img/@src')
        for i in images:
            with open("C:/Users/86135/Desktop/知乎图片链接.txt", 'at') as f:
                f.write(i+'\n')
        urls = url_re.findall(html.text)
        for url in urls:
            url = url+'\n'
            with open("C:/Users/86135/Desktop/知乎热榜.txt",'at') as f:
                f.write(url)
        contents = content_re.findall(html.text)
        for c in contents:
            with open("C:/Users/86135/Desktop/知乎热榜.txt",'at') as f:
                f.write('#'+c+'\n')
    
    if __name__ == '__main__':
        url = "https://www.zhihu.com/billboard"
        get_hot(url)

**运行结果如下：**  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2d1b3h1eWluZw_size_16_color_FFFFFF_t_70_pic_center]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2d1b3h1eWluZw_size_16_color_FFFFFF_t_70_pic_center]: /images/20210726/4bb5a98edd164ba49c2d299a33ad9b46.png