緩存就是將頁(yè)面信息下載下來(lái)，避免二次下載

import os
import requests
from pyquery import PyQuery as pq

"""
這個(gè)爬蟲(chóng)可以爬 10 個(gè)頁(yè)面, 把所有 TOP250 電影都爬出來(lái)
并且加入了緩存頁(yè)面功能
再也不用重復(fù)請(qǐng)求了(網(wǎng)絡(luò)請(qǐng)求很浪費(fèi)時(shí)間)
這樣做有兩個(gè)好處
    1, 增加新內(nèi)容(比如增加評(píng)論人數(shù))的時(shí)候不用重復(fù)請(qǐng)求網(wǎng)絡(luò)
    2, 出錯(cuò)的時(shí)候有原始數(shù)據(jù)對(duì)照(比如 消失的愛(ài)人 沒(méi)有 quote)
"""

class Model():
    def __repr__(self):
        name = self.__class__.__name__
        properties = ('{}=({})'.format(k, v) for k, v in self.__dict__.items())
        s = '\n<{} \n  {}>'.format(name, '\n  '.join(properties))
        return s


class Movie(Model):
    def __init__(self):
        self.name = ''
        self.other = ''
        self.score = 0
        self.quote = ''
        self.cover_url = ''
        self.ranking = 0

def cached_page(url):
    folder = 'cacheddouban'
    if not os.path.exists(folder):
        os.makedirs(folder)

    # https://movie.douban.com/top250?start=100
    filename = '{}.html'.format(url.split('=', 1)[-1])
    path = os.path.join(folder, filename)
    print(path)

    if os.path.exists(path):
        with open(path, 'rb') as f:
            s = f.read()
            return s
    else:
        # 發(fā)送網(wǎng)絡(luò)請(qǐng)求, 把結(jié)果寫(xiě)入到文件夾中
        r = requests.get(url)
        with open(path, 'wb') as f:
            f.write(r.content)
            return r.content

• 如果不存在目標(biāo)文件夾，則新建文件夾
• os.path 返回當(dāng)前文件的容器路徑

• 建立文件存儲(chǔ)頁(yè)面信息，文件名根據(jù)當(dāng)前 url 來(lái)
• os.path.join() 定位到當(dāng)前文件路徑

• 如果存在當(dāng)前路徑，讀取返回就行
• 如果不存在，就將獲取的頁(yè)面內(nèi)容存進(jìn)去

注意：
s == r.content

def movie_from_div(div):
    e = pq(div)
    m = Movie()
    m.name = e('.title').text()
    m.other = e('.other').text()
    m.score = e('.rating_num').text()
    m.quote = e('.inq').text()
    m.cover_url = e('img').attr('src')
    m.ranking = e('.pic').find('em').text()
    return m

def movies_from_url(url):
    page = cached_page(url)
    e = pq(page)
    items = e('.item')
    # 調(diào)用 movie_from_div 
    movies = [movie_from_div(i) for i in items]
    return movies

def main():
    for i in range(0, 250, 25):
        url = 'https://movie.douban.com/top250?start={}'.format(i)
        movies = movies_from_url(url)
        print('top250 movies', movies)

if __name__ == '__main__':
    main()