爬取猫眼电影

回顾之前学过的，经过一年考研，忘差不多了，要拾起来

import json
import re
from multiprocessing.pool import Pool

import requests
from requests.exceptions import RequestException
from selenium import webdriver

headers={
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"
        }
def get_one_page(url):
    try:
       # browser = webdriver.Chrome()　　　　　　　　　　//两种方法获取源码，requests必须要自加headers，webdriver不需要
        response =requests.get(url,headers=headers)
        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],

            'title': item[2],
            'actor': item[3].strip()[3:],
             'time': item[4].strip()[5:],
            'score': item[5]+item[6],
             '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) + '
')
        f.close()



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

if __name__ == '__main__':
    # for i in range(10):
    #     main(i*10)　　　　　　　　　　　　　　　　　　　
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])　　　　//多线程爬取，速度比较快