Requests+BeautifulSoup爬猫眼电影Top-100

import json
import requests
from bs4 import BeautifulSoup
from requests.exceptions import RequestException
def get_one_page(url):
    try:
        headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'            
        }
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None
def parse_one_page(html):
    soup = BeautifulSoup(html, 'lxml')
    title_images = soup.select('dd .image-link .board-img') 
    actors = soup.select('dd div div div .star')
    times = soup.select('dd div div div .releasetime')
    scores = soup.select('dd div div div .score')
    
    for t_i, actor, time in zip(title_images, actors, times):
        yield{
            'title':t_i['alt'],
            'image':t_i['data-src'],
            'actor':actor.get_text().strip()[3:],
            'time':time.get_text().strip()[5:]
        }
    
def write_to_file(content):
    with open('BS_Maoyan_Top100.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False)+ '\n')
        f.close()
def main(offset):
    url = 'https://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)
    
if __name__ == '__main__':
    for i in range(10):
        main(i*10)

你可能感兴趣的:(Requests+BeautifulSoup爬猫眼电影Top-100)