Python爬虫学习---正则抓取猫眼视频Top100信息

'''
Python3.7
bo 2018-06-02 15:30:22
'''

import json
from multiprocessing.pool import Pool

import requests
import re
from requests.exceptions import RequestException

def get_one_page(url):
    try:
        headers = {
            'Host': 'maoyan.com',
            'User-Agent': 'User-Agent  Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko',
            'Accept': '*/*',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN'
        }
        response = requests.get(url,headers=headers)
        if response.status_code == 200:
            return response.text
    except RequestException:
        return None

def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>' +
                         '.*?data-src="(.*?)"' +
                         '.*?name"><a.*?>(.*?)</a>'+
                         '.*?star">(.*?)</p>'+
                         '.*?releasetime">(.*?)</p>'+
                         '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            'index':item[0],
            'title': item[2],
            'score': item[5] + item[6],
            'actor':item[3].strip()[3:],
            'time':item[4].strip()[5:],
            'image': item[1],
        }
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 = 'http://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__':
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])