python 爬取猫眼下的榜单（一）--单个页面

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author: Dang Kai
# @Date: 2018-08-14 16:28:18
# @Last Modified time: 2018-08-14 17:37:20
# @E-mail: 1370465454@qq.com
# @Description:


# http://maoyan.com/board/4
# http://maoyan.com/board/4?offset=20

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


def get_one_page(url, headers):
    '''获取单页的html'''
    try:
        reponse = requests.get(url, headers=headers)
        if reponse.status_code == 200:
            return reponse.text
        else:
            return None
    except RequestException:  # 异常处理
        return None


def parse_one_page(html):
    '''正则匹配所需数据'''
    pattern = re.compile('
.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">'
                         + '.*?>(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                         + '.*?integer">(.*?).*?fraction">(.*?).*?', re.S)

    items = re.findall(pattern, html)
    # print(items)
    for item in items:
        yield{
            'index': item[0],
            'image': item[1],
            'title': item[2],
            'actor': item[3].strip()[3:],
            'starttime': item[4].strip()[5:],
            'score': item[5] + item[6]
        }
def write_to_file(content):
    '''写入文件'''
    with open('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n')
        f.close()



def main():
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'}
    html = get_one_page('http://maoyan.com/board/4?', headers)
    # print(html)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)
if __name__ == '__main__':
    main()