python网络爬虫实例

1、访问百度


from urllib.request import urlopen
url="http://www.baidu.com"
resp=urlopen(url)
 
with open("mybaidu.html",mode="w") as f:
    f.write(resp.read().decode("utf-8"))
print("over!")

2、输入单词百度翻译


import requests
url="https://fanyi.baidu.com/sug"
s=input("请输入你要翻译的英文单词")
dat={"kw":s}
#发送POST请求
resp=requests.post(url,data=dat)
print(resp.json())
resp.close()

3、豆瓣电影排行榜


 
import requests
url="https://movie.douban.com/j/chart/top_list"
param={"type": "24",
"interval_id": "100:90",
"action":"",
"start":"0",
"limit": "20"}
header={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36"}
#发送get请求
resp=requests.get(url,params=param,headers=header)
print(resp.json())
resp.close()

4、豆瓣电影top250


import requests
import re
url="https://movie.douban.com/top250"
header={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36"}
resp=requests.get(url,headers=header)
page_content=resp.text
obj=re.compile(r'
.*?.*?(?P.*?).*?.*?
(?P.*?) .*?(?P.*?).*?(?P.*?)人评价',re.S)

result=obj.finditer(page_content)
for it in result:
print(it.group("name"))
print(it.group("year").strip())
print(it.group("score"))
print(it.group("num"))
print("over!")

5、下载美女壁纸


import requests
from bs4 import BeautifulSoup
import time
url="https://www.umei.cc/bizhitupian/meinvbizhi/"
#header={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36"}
resp=requests.get(url)
resp.encoding='utf-8'
main_page=BeautifulSoup(resp.text,"html.parser")
alist=main_page.find("div",class_="item_list infinite_scroll").find_all("a")
for a in alist:
    href="http://umei.cc"+a.get("href")
    child_page_resp=requests.get(href)
    child_page_resp.encoding='utf-8'
    child_page=BeautifulSoup(child_page_resp.text,"html.parser")
    b=child_page.find("div",class_="big-pic")
    img=b.find("img")
    src=img.get("src")
    img_resp=requests.get(src)
    
    img_name=src.split("/")[-1]
    with open(img_name,mode="wb") as f:
        f.write(img_resp.content)
    print("over!",img_name)
    time.sleep(1)
print("all over!")