python3 爬虫学习之爬取猫眼电影

爬取猫眼电影排行榜

import re
import requests
from multiprocessing import Pool
from requests.exceptions import RequestException
import time
print(time)
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
import json
def get_open_page(url):
    try:
        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>.*?<a href=.*?title="(.*?)" class.*?<img src="(.*?)" alt.*?    <p class="star">(.*?)</p>.*?</dd>',re.S)
    items=re.findall(pattern,html)
    for item in items:
        yield {
            'index':item[0],
            'image':item[1].strip()[2:],
            'actor':item[2].strip()
        }
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_open_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)])
    print(time)