爬虫笔记1

requests库抓取数据

URL（uniform resource locator ，统一资源定位符），由协议+域名+路径+参数组成

HTTP请求格式（请求行，请求头，空行，请求体）

常见请求方法：

1.GET

import     requests
def  get_one_img():
   #url="https://p1.meituan.net/movie/6bea9af4524dfbd0b668eaa7e187c3df767253.jpg@464w_644h_1e_1c"
   url = "https://p1.meituan.net/movie/b607fba7513e7f15eab170aac1e1400d878112.jpg@464w_644h_1e_1c"
   headers={
      "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.67"
   }
   #功能  参数  返回值
   res=requests.get(url,headers=headers)
   print(res)

   with open("kill.jpg",'wb')  as  f:
      f.write(res.content)
#get_one_img()

def get_img(url, name):
   headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.67"}
   # 功能  参数  返回值
   res = requests.get(url, headers=headers)
   # print(res)
   img_name = f"{name}.jpg"
   with open("img_name", 'wb')  as  f:
      f.write(res.content)
url = "https://p0.meituan.net/movie/283292171619cdfd5b240c8fd093f1eb255670.jpg@464w_644h_1e_1c"
name = '2'
get_img(url,name)

2.POST

正则：利用文字结构

接下来是利用requests库抓取图片的代码

import re

import     requests

def  get_one_img():
   #url="https://p1.meituan.net/movie/6bea9af4524dfbd0b668eaa7e187c3df767253.jpg@464w_644h_1e_1c"
   url = "https://p1.meituan.net/movie/b607fba7513e7f15eab170aac1e1400d878112.jpg@464w_644h_1e_1c"
   headers={
      "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.67"
   }
   #功能  参数  返回值
   res=requests.get(url,headers=headers)
   #print(res)

   with open("boat.jpg",'wb')  as  f:
      f.write(res.content)
get_one_img()

def get_img(url,name):
    headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.67"}
    res=requests.get(url,headers=headers)
    img_name=f"{name}.jpg"
    with open(img_name,'wb')  as  f:
        f.write(res.content)
# url="https://p0.meituan.net/movie/da64660f82b98cdc1b8a3804e69609e041108.jpg@464w_644h_1e_1c"
# name='1'
# get_img(url,name)

def get_urls():
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.67"
    }
    #接下来不在手动，直接向网页发起请求抓取
    res=requests.get("https://ssr1.scrape.center/",headers=headers)
    text=res.text#变成文本
    urls=re.findall('src="(https.*?)"',text)
    return urls
urls=get_urls()

for index,url in enumerate(urls):
    get_img(url,index)

接下来是利用requests库抓取文本信息

注意：比较重要的文本信息需要提取

xpath：利用网页结构