m0_52432374的博客

import requests from lxml import etree url = 'https://kunming.zbj.com/search/f/?kw=sass' resp = requests.get(url) # print(resp.text) html = etree.HTML(resp.text) # 拿到单个服务商的信息 divs= html.xpath("/html/body/div[6]/div/div/div[2]/div[7]/div/div") for div in d

import requests from lxml import etree url = "https://beijing.zbj.com/search/f/?type=new&kw=saas" resp = requests.get(url) # print(resp.text) # 解析 html = etree.HTML(resp.text) # 拿到每一个服务商的div divs = html.xpath("/html/body/div[6]/div/div/div[2]/div[4]

# 1.拿到主页面的源代码. 然后提取到子页面的链接地址, href # 2.通过href拿到子页面的内容. 从子页面中找到图片的下载地址 img -> src # 3.下载图片 import requests from bs4 import BeautifulSoup import time url = "https://www.umei.cc/bizhitupian/weimeibizhi/" resp = requests.get(url) resp.encoding = 'utf-8' #

import json import requests def get_content_list(): from lxml import etree base_url = "http://news.4399.com/gonglue/kpct/kapai/" resp = requests.get(base_url) #输出状态码 # print(resp) #输出源代码 # print(resp.content.decode("gbk"))