猫眼电影榜单爬虫-优快云博客

本文链接：https://blog.youkuaiyun.com/Py_CCY/article/details/76156031

本文介绍了一个使用Python实现的猫眼电影榜单爬虫程序，该程序利用requests库获取网页内容，并采用正则表达式解析电影信息，最终将数据保存为HTML格式。通过多进程并行处理，提高了数据抓取效率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import requests
from requests.exceptions import RequestException
from multiprocessing.dummy import Pool
import re

def get_one_page(url):
    try:
        r = requests.get(url)
        if r.status_code == 200:
            return r.text
        return None
    except RequestException:
        return None
def parser_one_page(html):
    pattern = re.compile("<dd>.*?>(\d+)</i>.*?data-src=\"(.*?)\".*?name\">.*?>(.*?)"
                         "<.*?</p>.*?star\">(.*?)"
                         "</p>.*?releasetime\">(.*?)"
                         "</p>.*?integer\">(.*?)</i>.*?fraction\">(.*?)</i>",re.S)

    links = re.findall(pattern,html)
    for link in links:
        yield {
            'index':link[0],
            'image':link[1],
            'title':link[2],
            'actor':link[3].strip(),
            'time':link[4].strip(),
            'score':link[5]+link[6]
        }
def main(page_num):
    url='https://maoyan.com/board/4?offset='+str(page_num)
    html = get_one_page(url)
    links = parser_one_page(html)

    with open("maoyan.html",'a',encoding="utf-8") as f:
        f.write('<html>')
        f.write('<head><meta charset="UTF-8"></head>')
        f.write('<body>')
        f.write('<table>')
        for link in links:
            f.write("<tr>")
            f.write("<td>%s</td>" % link['index'])
            f.write("<td>%s</td>" % link['actor'])
            f.write("<td>%s</td>" % link['title'])
            f.write("<td><img src=\"%s\"></td>" % link['image'])
            f.write("<td>%s</td>" % link['time'])
            f.write("<td>%s</td>" % link['score'])
            f.write("</tr>")
        f.write('</table>')
        f.write('</body>')
        f.write('</html>')
if __name__ == '__main__':
    pool=Pool()
    pool.map(main,[i*10 for i in range(10)])

python_猫眼实例