猫眼top100电影信息爬虫

import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool
import os
from hashlib import md5

def get_one_page(url):
    user_agent = "Mozilla"
    headers = {"User-Agent": user_agent}  # 将爬虫隐藏为Mac用户（固定格式）
    try:
        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):
    pattern = re.compile(r'<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name.*?title="(.*?)".*?star">(.*?)'
                        '</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            '排名': item[0],
            '图片': item[1],
            '标题': item[2],
            '演员': item[3].strip()[3:],
            '时间': item[4].strip()[5:],
            '评分': item[5] + item[6]
        }

def write_to_file(content):
    with open("maoyan_top_1oo.txt", 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')     # 字典转字符串
        f.close()


def download_images(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            print("正在下载" + url)
            save_images(response.content)
        return None
    except RequestException:
        print(url + "下载失败")

def save_images(content):
    file_path = '{0}/{1}.{2}'.format("F:/anaconda/猫眼_top100", md5(content).hexdigest(), "jpg")
    if not os.path.exists(file_path):
        with open(file_path, "wb") as f:
            f.write(content)
            f.close()


def main(offset):
    url = "http://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)
        download_images(item["图片"])

if __name__ == "__main__":
    '''
    for i in range(10):
        main(i * 10)
    '''
    pool = Pool()
    pool.map(main, [i*10 for i in range(10)])
    pool.close()
    pool.join()  # 主进程阻塞等待子进程的退出
    print("爬取结束！")