Python爬虫：requests+正则爬取猫眼最受期待榜单

# 基本思路：
# 1.浏览访问网页榜单-最受期待榜 url = 'http://maoyan.com/board/6?offset=0'
# 2.获取数据：电影名称 主演 网址 上映时间 本月新增想看人数 总想看人数
# 3.数据解析处理等
# 4.数据保存

import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool           # 多线程

def get_page(url):        # 网页请求
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        else:
            return None
    except RequestException as e:
        return e

def analysis(html):  # 解析网页数据
    pattern = re.compile('.*?<p class="name".*?data-val.*?>(.*?)</a></p>.*?class="star">(.*?)\
</p>.*?class="releasetime">(.*?)</p>.*?class="month-wish">(.*?)<span>.*?class="stonefont">.*?</span>.*?\
class="total-wish">(.*?)<span>.*?class="stonefont">.*?</span>', re.S)  # re.S 匹配换行符
    result = re.findall(pattern, html)
    for item in result:
        yield {
            'name': item[0],
            'actor': item[1].strip()[3:],
            'time': item[2].strip()[5:],
            'month_wish': item[3],
            'total_wish': item[4]
        }

def write_to_file(content):         # 数据保存至本地
    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 = 'http://maoyan.com/board/6?offset=' + str(offset)
    html = get_page(url)
    for item in analysis(html):
        print(item)
        # write_to_file(item)

if __name__ == '__main__':
    """
    for i in range(0,4):
        main(i*10)
        """
    pool = Pool()
    pool.map(main, [i*10 for i in range(0, 4)])