猫眼数据爬取

import json
import re
import requests
from requests.exceptions import RequestException
# 伪造：UserAgent，某些网站会识别python爬虫程序并阻断,通过构造User_Agent可以抵抗某些反爬虫机制
from fake_useragent import UserAgent

from multiprocessing import Pool
ua = UserAgent()


# 获取数据
def get_one_page(url):
    headers = {
        'User-Agent': ua.random}
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None


# 解析数据
def parse_one_page(html):
    # 正则表达式字符串
    pattern = re.compile('
.*?board-index.*?>(\d+)<.*?
                         + '.*?data-src="(.*?)".*?.*?star">[\\s]*(.*?)[\\n][\\s]*
.*?'
                         + 'releasetime">(.*?)
.*?integer">(.*?).*?'
                         + 'fraction">(.*?).*?
', re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2],
            'actor': item[3].strip()[3:],
            'time': item[4].strip()[5:],
            'score': item[5] + item[6]
        }


#
def write_to_file(content):
    with open('result.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):
        write_to_file(item)


if __name__ == '__main__':
    for i in range(10):
        main(i * 10)
        print('爬取数据完成啦')