Python爬取公众号文章的图片的示例

一、示例代码：

# 爬虫爬取微信公众号文章中的图片
import requests
from lxml import etree

test_url = 'https://mp.weixin.qq.com/s/AH7tdFR_QGTMg2wxaj0sog'
headers = {
    'host': 'mp.weixin.qq.com',
    'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:109.0) Gecko/20100101 Firefox/117.0'
}


# 下载图片的函数定义
def download_pic(url):
    print('download pic:' + url)
    try:
        pic_name = url.split('/')[-2]
        fmt = url.split('=')[-1]
        img_resp = requests.get(url).content
        with open(pic_name + '.' + fmt, 'wb+') as f:
            f.write(img_resp)
    except Exception as reason:
        print(str(reason))


# Xpath解析下载的函数定义
def get_pic(content):
    img_list = content.xpath('//img/@data-src')
    for img in img_list:
        download_pic(img)


if __name__ == '__main__':
    res = requests.get(url=test_url, headers=headers).text
    html = etree.HTML(res)
    get_pic(html)

二、要点说明：

不得不说，比较之后会发现，Xpath解析确实是最快、适用性最强的解析方法，毕竟Xpath语法底层是C语言开发的。