BeautifulSoup解析网页

import requests
from bs4 import BeautifulSoup
import re
url='https://movie.douban.com/chart'
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}
f=requests.get(url,headers=headers).text

from lxml import etree


pattern = re.compile(r'<[^>]+>', re.S)

result = pattern.sub('',f)

print(result)





我已经用这个成功解析了网页，并删除了一大推的字符，可不可以再帮忙看看，怎样彻底筛选出里面的所有汉字

import requests
from bs4 import BeautifulSoup

url='https://movie.douban.com/chart'
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}
f=requests.get(url,headers=headers).text

soup = BeautifulSoup(f,"lxml")
div1 = soup.find("div",{"class":"indent"})
table = div1.find_all("table",{"width":"100%"})
for t in table:
    print(t.find("div",{"class":"pl2"}).a.text.strip(),"\n",
          t.find("div", {"class": "pl2"}).a['href'],"\n",
          t.find("div",{"class":"pl2"}).p.text,"\n",
          t.find("div",{"class":"pl2"}).div.find("span",{"class":"pl"}).text,"\n",)

import requests
from bs4 import BeautifulSoup

url='https://movie.douban.com/chart'
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}
f=requests.get(url,headers=headers).text

soup = BeautifulSoup(f,"lxml")
div1 = soup.find("div",{"class":"indent"})
table = div1.find_all("table",{"width":"100%"})
for t in table:
    print(t.find("div",{"class":"pl2"}).a.text.strip(),"\n",
          t.find("div", {"class": "pl2"}).a['href'],"\n",
          t.find("div",{"class":"pl2"}).p.text,"\n",
          t.find("div",{"class":"pl2"}).div.find("span",{"class":"pl"}).text,"\n",)

1. import requests
   
2. from bs4 import BeautifulSoup
   
3. 
   
4. url='https://movie.douban.com/chart'
   
5. headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}
   
6. f=requests.get(url,headers=headers).text
   
7. 
   
8. soup = BeautifulSoup(f,"lxml")
   
9. div1 = soup.find("div",{"class":"indent"})
   
10. table = div1.find_all("table",{"width":"100%"})
    
11. for t in table:
    
12.     print(t.find("div",{"class":"pl2"}).a.text.strip(),"\n",
    
13.           t.find("div", {"class": "pl2"}).a['href'],"\n",
    
14.           t.find("div",{"class":"pl2"}).p.text,"\n",
    
15.           t.find("div",{"class":"pl2"}).div.find("span",{"class":"pl"}).text,"\n",

复制代码

单数据提取，在重组.

import requests
import re
url='https://movie.douban.com/chart'
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}
f=requests.get(url,headers=headers).text
listurl = re.findall(r'<a.*href="(.*?)".*?title="(.*?)">',f)
print(listurl)

listurl = re.findall(r'<a.*href="(.*?)".*?title="(.*?)">',f)
for i in listurl:
    print(i)