python3.6 利用requests和正则表达式爬取猫眼电影TOP100

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

def get_one_page(url):
    try:
        headers = {"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0"}
        response = requests.get(url,headers=headers)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_parge(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],
            'image':item[1],
            'title':item[2],
            'actor':item[3].strip()[3:],
            'time':item[4].strip()[5:],
            'score':item[5]+item[6]
        }

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 = 'https://maoyan.com/board/4?offset='+str(offset)
    html = get_one_page(url)
    for item in parse_one_parge(html):
        print(item)
        write_to_file(item)

if __name__ == '__main__':
    for i in range(10):
        main(i*10)
    # pool = Pool()
    # pool.map(main, [1*10 for i in range(10)])

 

posted @ 2018-07-03 17:40  ESHLkangi  阅读(352)  评论(0编辑  收藏  举报