python爬虫两个影院的实例

主要两个的python代码如下：

import requests
from bs4 import BeautifulSoup
url = 'https://www.17k.com/'
headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'}
response =  requests.get(url,headers = headers)
content = response.content.decode('utf-8')
soup = BeautifulSoup(content, 'html.parser')
listA = soup.find_all(name='ul',attrs={"class":"Top1"})
a=0
movie_list=[]
for each in listA:
    all1=each.find("li").a.get("href").strip()
    all2=each.find("li").a.text.strip("[]")
    movie_list.append([" 电影名： ",all2,"电影链接： ",all1])
with open("17kmovie.txt","w+",encoding="utf-8") as f:
    for i in range(len(movie_list)):
        f.write(str(movie_list[i]))
        f.write("
")
    f.close()

import requests
from bs4 import BeautifulSoup

def get_movie():
    url = 'https://movie.douban.com/top250'  #请求地址
    headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'}#创建头部信息
    movie_list=[]
    for i in range(0,10):
        url = 'https://movie.douban.com/top250?start='+str(i*25)
        response=requests.get(url,headers=headers)
        soup=BeautifulSoup(response.text,"html.parser")
        div_list = soup.find_all('div', class_='info')
        for each in div_list:
            title = each.find('div', class_="hd").span.text.strip()
            title2 = each.find('div', class_="hd").a.get("href").strip()
            info = each.find('div', class_='bd').p.text.strip()
            info = info.replace('\n', '').replace('\xa0', '')
            info = ' '.join(info.split())
            star = each.find('span', class_='rating_num').text.strip()
            people = each.find('div', class_='star').contents[7].text.strip()
            movie_list.append(["电影名： ",title, "电影链接  ",title2,info, star, people])
    return movie_list
movie=[]
movie=get_movie()
with open("Top_movie_250.txt","w+",encoding="utf-8") as f:
    for i in range(len(movie)):
        f.write(str(movie[i]))
        f.write("
")
    f.close()

实验结果如下：

将其写到文件中：

 用到的都是之前学到的知识点。

（发现的文体是。有的时候例如span语句，存在没有改属性的情况。进而获得text会出现属性失败的错误。最后自己发现通过测试解决的）