python获取电影天堂各版块电影

#-*-coding:UTF-8-*-
import re
import requests
import json
from lxml import etree

weburl =r"http://www.ygdy8.net"

def getpage(url):   #获取电影列表页面数
    t= requests.get(url)
    t.encoding='gbk'
    t=''.join(re.findall("/(\d+)条",t.text))
    sum=int(t) // 25
    if int(t) % 25 != 0:
        sum+=1
    return sum

def getlist(url):   #获取电影列表页各个电影URL
    t=requests.get(url)
    t.encoding='gbk'
    #html = etree.HTML(t.text)
    #murl = html.xpath('//*[@class="ulink"][email protected]')
    murl = re.findall('(/html/.*?/.*?/\d+/\d+.html)" class="ulink"',t.text)
    #mname= html.xpath('//*[@class="ulink"]/text()')
    return murl

def getdownurl(url):    #获取电影页下载地址
    t = requests.get(url)
    t.encoding = 'gbk'
    if len(re.findall('fdfddf"><a href="(.*?)"',t.text))>0 :
        ftpurl= re.findall('fdfddf"><a href="(.*?)"',t.text)[0]
        return ftpurl
    else:
        return ''

def getdbdata(moivename):   #获取豆瓣评分
    dburl =r"http://api.douban.com/v2/movie/search?q="+moivename
    txt=requests.get(dburl)
    l=json.loads(txt.text)
    #dbid=l["subjects"][0]["id"]
    #dbweburl=l["subjects"][0]["alt"]
    if 'code' in l.keys():
        return -1
    else:
        dbpf=l["subjects"][0]["rating"]["average"]
        return dbpf

def getgf(url): #获取高评分电影
    for i in range(1,5):
        if i==1:
            t = requests.get(url+'.html')
        else:
            t = requests.get(url +'_'+ str(i) + '.html')
        t.encoding = 'gbk'
        tmp=re.findall('href="(http://www\.ygdy8\..*?/html/gndy/.*?/\d+/\d+\.html)',t.text)
        for j in tmp:
            durl=getdownurl(j)
            if durl != '':
                name = ''.join(durl).split('.')
                moivename = (name[5] + '[' + name[6] + name[7] + ']')
                dbpf = getdbdata(name[5])
                if dbpf == -1:
                    print(moivename,'下载地址：'+ durl)
                else:
                    if dbpf > 7.9:
                        print(moivename,'豆瓣评分：'+ str(dbpf),'下载地址：'+ durl)

def getmoive(id,page):  #获取指定版块指定页数的电影下载地址
    if id < 3:
        pagenum=getpage(url[id]+'1.html')
        if pagenum < page:
            page=pagenum
        for i in range(1,page+1):
            tmpurl=getlist(url[id]+str(i)+'.html')
            k=0
            for j in tmpurl:
                downurl=getdownurl(weburl+j)
                name=''.join(downurl).split('.')
                moivename=(name[5]+'['+name[6]+name[7]+']')
                dbpf=getdbdata(name[5])
                if dbpf == -1:
                    print(moivename,'下载地址：'+ downurl)
                else:
                    print(moivename,'豆瓣评分：'+str(dbpf),'下载地址：'+downurl)
                k+=1
    else:
        getgf(url[3])

#几个电影版块的URL
url = [                                                         #分类名称   id
    'http://www.ygdy8.net/html/gndy/dyzz/list_23_',     #最新电影   0
    'http://www.ygdy8.net/html/gndy/china/list_4_',     #国内电影   1
    'http://www.ygdy8.net/html/gndy/oumei/list_7_',     #欧美电影   2
    'http://www.ygdy8.net/html/gndy/jddy/20160320/50510'#高分经典  3
]

if __name__=='__main__':
    getmoive(0,3)   #getmoive(分类ID,获取页数)     ps:每页是25部电影