requests爬取猫眼电影top100

import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool
def page_one_html(url):
    try:
        response = requests.get(url);
        if response.status_code == 200:
            return response.text
        else:
            return None
    except RequestException:
        return None

def parse_page_html(content):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?title="(.*?)".*?data-src="(.*?)".*?'
                         +'star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>'
                         +'.*?</dd>',re.S)
    items = re.findall(pattern,content)
    #print(items)
    for item in items:
        yield{
            "index":item[0],
            "title": item[1],
            "image":item[2],
            "actor":item[3].strip()[3:],
            "createTime":item[4].strip()[4:],
            "score":str(item[5])+str(item[6])
        }

def write_text(item):
    with open("result.txt","a",encoding="utf-8") as f:
        f.write(json.dumps(item,ensure_ascii=False) + "\n")
        f.close()


def main(offset):
    url = "http://maoyan.com/board/4?offset="+str(offset)
    html = page_one_html(url)
    #print(html)
    for item in parse_page_html(html):
        write_text(item)

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

 from requests.exceptions import RequestException 异常处理很重要

import re 

import json

from multiprocessing import Pool 线程池下线搜搜的