笔记-多进程抓取猫眼TOP100

今天为大家介绍使用requests模块和正则表达式配合抓取

#coding:utf-8
from requests.exceptions import RequestException
import requests
import re
import json
from multiprocessing import Pool
def get_one_page(url):
    try:
        headers={
            'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36'
        }
        response=requests.get(url,headers=headers)
        if response.status_code==200:
            response.encoding=response.apparent_encoding
            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'
                       +'.*?data-val.*?>(.*?)</a>.*?star">(.*?)</p>'
                       +'.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i></p>',re.S)
    items=re.findall(pattern,html)
    for item in items:
        yield{生成一个生成器，装入字典
            'index':item[0],
            'image':item[1],
            'title':item[2],
            'actor':item[3].strip()[3:],
            'time':item[4].strip()[5:],
            'score':item[5]+item[6]
        }
    print(items)


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(url):
    url='http://maoyan.com/board/4?offset=%s'%url
    html=get_one_page(url)
    for item in parse_one_page(html):
        write_to_file(item)

if __name__=='__main__':
        pool=Pool()实例化
        pool.map(main,[i*10 for i in range(10)])#开启进程

以上就是抓取的全部代码了查看下结果文件