python爬虫知识点总结（九）Requests+正则表达式爬取猫眼电影

一、爬取流程

二、代码演示

#-*- coding: UTF-8 -*-
#_author:AlexCthon
#mail:[email protected]
#date:2018/8/3

import requests
from multiprocessing import Pool # 进程池，用来实现秒抓
from requests.exceptions import RequestException
import re
import json
def get_one_page(url):
    try:
        response = requests.get(url)
        #print(response.text)
        if(response.status_code == 200):
            return response.text
        return None
    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],
            '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 = 'http://maoyan.com/board/4?offset='+str(offset)
    html = get_n=get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

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