使用Beautiful Soup爬取猫眼TOP100的电影信息,将排名、图片、电影名称、演员、时间、评分等信息,提取的结果以文件形式保存下来。
import time import json import requests from bs4 import BeautifulSoup def get_one_page(url): try: headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'} response = requests.get(url, headers=headers) response.encoding = response.apparent_encoding if response.status_code == 200: return response.text else: return None return None except RequestException: return None def parse_one_page(text): soup = BeautifulSoup(text, 'lxml') ranking = soup.select('dd .board-index') imgsrc = soup.select('#app > div > div > div.main > dl > dd > a > img.board-img') title = soup.select('#app > div > div > div.main > dl > dd > a') star = soup.find_all(name='p', class_='star') #star = soup.select('#app > div > div > div.main > dl > dd > div > div > div.movie-item-info > p.star') releasetime = soup.find_all(name='p', class_='releasetime') interger = soup.find_all(name='i', class_='integer') fraction = soup.find_all(name='i', class_='fraction') for i in range(10): yield { 'index': ranking[i].string, 'image': imgsrc[i].attrs['data-src'], 'title': title[i]['title'], 'actor': star[i].string.strip()[3:], 'time': releasetime[i].string.strip()[5:], 'score': interger[i].string + fraction[i].string } def write_to_file(content): with open('maoyan.txt', 'a', encoding='utf-8') as f: f.write(json.dumps(content, ensure_ascii=False)+'\n') def main(offset): url = 'https://maoyan.com/board/4?offset=' + str(offset) text = get_one_page(url) for item in parse_one_page(text): print(item) write_to_file(item) if __name__ == '__main__': for i in range(10): main(offset=i*10) time.sleep(1)