python3爬取猫眼top100电影信息

import requests

from requests.exceptionsimport RequestException

import re

import json

from multiprocessing import Pool

def get_one_page(url):

try:

response = requests.get(url)

if response.status_code ==200:

return response.text

return None

    except RequestException:

return None

def parse_one_page(html):

pattern = re.compile('.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">

                        +'.*?>(.*?).*?star">(.*?).*?releasetime">(.*?)'

                        +'.*?integer">(.*?).*?fraction">(.*?).*?',re.S)

items = re.findall(pattern,html)

# print(items)

    for itemin items:

yield {

            '排名': item[0],

            '图片': item[1],

            '名称': item[2],

            '演员': item[3].strip()[3:],

            '时间': item[4].strip()[5:],

            '评分': 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" +str(offset)

html = get_one_page(url)

# print(html)

# parse_one_page(html)

    for item_ain parse_one_page(html):

print(item_a)

write_to_file(item_a)

if __name__ =="__main__":

# for i in range(10):

#    main(i*10)

    pool = Pool()

pool.map(main,[i*10 for iin range(10)])