猫眼练手

猫眼t100.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Author;Tsukasa
import json
import re
import pandas as pd
import requests
from requests.exceptions import RequestException
from multiprocessing import Pool

User_Agent = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36'}

def get_one_page(url):
    try:
        res = requests.get(url,'lxml')
        if res.status_code == 200:
            return res.text
        return print('请求错误代码:',res.status_code)
    except RequestException:
        return None

def get_re_one_page(html_text):
    re_set = re.compile('<dd>.*?">(\d+)</i>.*?title="(.*?)".*?data-src="(.*?)".*?class="star">(.*?)</p>.*?class="releasetime">(.*?)</p>.*?class="integer">(.*?)</i>.*?class="fraction">(.*?)</i>',re.S)
    re_get_html = re.findall(re_set,html_text)
    for i in re_get_html:
        yield {
            '排名':i[0],
            '片名':i[1],
            '封面链接':i[2],
            '主演':i[3].lstrip().lstrip('主演：').rstrip(),
            '上映时间':i[4].lstrip('上映时间：'),
            '评分':i[5] + i[6]
        }

def writer_to_text(text):
    with open('TOP 100.text','a',encoding='utf-8')as f:
        f.write(json.dumps(text,ensure_ascii=False)+'\n')
        f.close()

def pandas_to_xlsx(pd_list):
    pd_look = pd.DataFrame(pd_list)
    pd_look.to_excel('Top 100.xlsx',sheet_name='猫眼Top100')

data = []
def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    print(url)
    html_text = get_one_page(url)
    for i in get_re_one_page(html_text):
        writer_to_text(i)
        data.append(i)

if __name__ == '__main__':
    for i in range(10):
        main(i*10)
    pandas_to_xlsx(data)