2019.10.09 猫眼电影爬虫

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


# 定义一个函数获取网页的内容
def get_one_page(url):
    try:
        headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
        # 尽量加上header：进入网页后右键检查，选择network，Ctrl+R后随便选一个文件即可获得header
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
        # 判断是否正常获得网页内容
        return None
    except RequestsException:
        return None

# 定义一个函数获取我们想要的内容的文件，使用正则表达式
def parse_one_page(html):
    pattern = re.compile('
.*?board-index.*?>(\d+).*?data-src="(.*?)".*?movie-item-info.*?title="(.*?)".*?'
                         + 'star">(.*?)
.*?releasetime">(.*?)
.*?score-num.*?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]
        }

# 定义一个函数将文件写出
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()

# 实现翻页功能
def main(offset):
    url = 'https://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    parse_one_page(html)
    for item in parse_one_page(html):
        write_to_file(item)


if __name__ == '__main__':
    pool = Pool()
    pool.map(main, [i * 10 for i in range(10)])