微信文本的爬取

import requests
from lxml import etree
# User-Agent:Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36

def body():
    url = "https://mp.weixin.qq.com/s/aPYBMeS9ZHY0q41xiv_Afw"
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'}
    respones = requests.get(url,headers=header)
    # print(respones)
    respones.encoding = "utf_8"
    html = respones.text
    obj = etree.HTML(html)
    obj_1 = obj.xpath('//div[@class="rich_media_content "]/p/strong/img/@data-src')
    obj_2 = obj.xpath('//div[@class="rich_media_content "]/p/img/@data-src')
    obj_3 = obj.xpath('//div[@class="rich_media_content "]/p/span/strong/img/@data-src')
    obj_4 = obj.xpath('//div[@class="rich_media_content "]/p/span/strong/span/img/@data-src')
    obj_5 = obj.xpath('//div[@class="rich_media_content "]/p/strong/span/img/@data-src')
    obj_6 = obj.xpath('//div[@class="rich_media_content "]/p/img/@src')
    obj_body = obj_1 + obj_2 + obj_3 + obj_4 + obj_5 + obj_6


    for i in obj_body:
        r = requests.get(i)
        with open(r"F:\day08\人民日报\微信图片\%s.jpg"%i[-30:-20],"wb") as f:
            f.write(r.content)

body()

　　

转载于:https://www.cnblogs.com/heluobing/p/10872659.html