'''
程序目的:
1.提取豆瓣Top250電影，按照序號，名稱，豆瓣評分給出
'''

import requests
import re

#抓取網(wǎng)頁
def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

#分析網(wǎng)頁，提取所需信息
def parseHTML(info,html):
    info = []
    try:
        tlt = re.findall(r'\"title\"\>[\u4e00-\u9fa5]+',html)
        rlt = re.findall(r'\"v:average\"\>[0-9]\.[0-9]',html)  
        
        for i in range(len(tlt)):      #電影個數(shù)
            title = tlt[i].split('>')[1]   #用>隔開
            rank = rlt[i].split('>')[1]   #用>隔開
            info.append([title,rank])
    except:
        print("")

def printInfo(info):
    tplt = "{:5}\t{:10}\t{:10}"
    print(tplt.format("序號","電影名稱","豆瓣評分"))
    count = 0
    for g in info:
        count = count + 1
        print(tplt.format(count,g[0],g[1]))
        
def main():
    start_url = "https://movie.douban.com/top250?start"
    depth = 9   #總共10頁
    infomation = [] #用來存儲相關(guān)信息

    for i in range(depth):
        try:
            url = start_url+str(25*i)
            html = getHTMLText(url)
            parseHTML(infomation,html)
        except:
            continue
    printInfo(infomation)
main()