ofweekjixie

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://gongkong.ofweek.com/2019-04/ART-310005-11000-30318220_4.html"
    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 = "gbk"
    html = respones.text
    obj = etree.HTML(html)
    obj_titer = obj.xpath('//div[@id="articleC"]/p/strong/img/@src')
    obj_text = obj.xpath('//div[@id="articleC"]/p/strong/text()')
    print(obj_titer )
    print(len(obj_titer))
    print(obj_text)
    print(len(obj_text))
    ret = len(obj_titer)
    s = range(29,29+ret)
    for i,d in zip(obj_titer,s):
        reg = requests.get(i)
        with open(r"F:\day08\人民日报\微信图片\%s.jpg"%d,"wb",) as f:

            f.write(reg.content)

　　

转载于:https://www.cnblogs.com/heluobing/p/10928748.html