使用requests模块爬取豆瓣电影top50数据

来上代码

import requests
import re
import json
import time


# 获取一页的数据
def get_one_page(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; U; Mac OS X Mach-O; en-US; rv:2.0a) Gecko/20040614 Firefox/3.0.0 "
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    return None

#
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(html)
        write_to_file(item)

#
def parse_one_page(html):
    pattern = re.compile(
        '<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>',
        re.S
    )
    items = re.findall(pattern, html)
    print(items)
    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2].strip(),
            'actor': item[3].strip()[3:] if len(item[3]) > 3 else '',
            'time': item[4].strip()[5:] if len(item[4]) > 5 else '',
            'score': item[5].strip() + item[6].strip()
        }


def write_to_file(content):
    with open('result.txt', 'a', encoding='utf-8') as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content, ensure_ascii=False) + '\n')


if __name__ == '__main__':
    for i in range(10):
        main(offset=i * 10)
        time.sleep(1)

可以关注微信公众号：幽灵邀请函 获取更多学习资源