|

楼主 |
发表于 2021-11-2 10:55:47
|
显示全部楼层
import requests,os,urllib,re
from lxml import etree
import string
import binascii
#代理模块
proxies = {
"http" : "http://127.0.0.1:10809" ,
"https" : "http://127.0.0.1:10809" ,
}
#请求目标网址
target="http://www.fangongheike.com/"
req = requests.get(url=target, proxies=proxies)
req.encoding='utf-8'
#获取整个网页
html = etree.HTML(req.text)
#抓取图片url
img_url = html.xpath("//div[@class='post-body entry-content']/div[@class='separator']/a/@href")
print(img_url)
#for i in img_url:
# img_src = requests.get(url=i, proxies=proxies)
# print(type(img_src)) |
|