爬取猫眼Top100

import requests
import re
from bs4 import BeautifulSoup

def get_page(page):
    url = 'https://maoyan.com/board/4?offset=' + str(page)
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3551.3 Safari/537.36"}
    response = requests.get(url, headers=headers)
    html = response.text
    return html
    
def parse_info(html):
    soup = BeautifulSoup(html, 'lxml')  
    sort = [s.string for s in soup.find_all(class_=re.compile("board-index board-index"))]
    stars = [star.string.strip().replace("主演：", "") for star in soup.find_all(class_="star")]
    names = [name.string.strip() for name in soup.find_all(class_="name")]
    releasetimes = [time.string.strip().replace("上映时间：", "") for time in soup.find_all(class_="releasetime")]
    scores = []
    for s in soup.find_all(class_="score"):
        score = s.find(class_="integer").string+s.find(class_="fraction").string
        scores.append(score)
    return list(zip(sort, names,stars,releasetimes,scores))
    
def save_data(info):
    with open('movie.txt', 'a', encoding='utf-8') as f:
        for item in info:
            f.write(str(item) + '\n')

for page in range(10):
    print("正在获取第{}页信息。。。".format(page+1))
    html = get_page(page*10)
    info = parse_info(html)
    save_data(info)