from lxml import etree
import requests
# url='https://www.dytt8.net/html/gndy/dyzz/index.html'
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, '
                 'like Gecko) Chrome/83.0.4103.61 Safari/537.36'
}

# 爬取前八页的电影的链接
def Film_urls():
    url='https://www.dytt8.net/html/gndy/dyzz/list_23_{}.html'
    Base_url='https://www.dytt8.net/'
    urls=[]
    for i in range(1,8):
        print("正在爬取每页电影链接。。。。")
        url=url.format(i)
        response=requests.get(url,headers=headers)
        html=etree.HTML(response.text)
        urls+=(html.xpath("//table[@class='tbspan']//a/@href"))
    urls=[Base_url+url for url in urls]
    return urls

# 爬取每个电影的详细内容
def Film_content(url):
    movie={}
    response=requests.get(url,headers=headers)
    response=response.content.decode(encoding='gbk',errors='ignore')
    html=etree.HTML(response)
    content=html.xpath("//div[@id='Zoom']")[0]


    #定义筛选函数
    def parse_info(info,str):
        return info.replace(str,"").strip()

    infos=content.xpath(".//text()")
    for index,info in enumerate(infos):
        if info.startswith("◎片　　名"):
            info=parse_info(info,"◎片　　名")
            movie['name']=info
        elif info.startswith("◎年　　代"):
            info=parse_info(info,"◎年　　代")
            movie['year']=info
        elif info.startswith("◎产　　地"):
            info=parse_info(info,"◎产　　地")
            movie['country']=info
        elif info.startswith("◎类　　别"):
            info=parse_info(info,"◎类　　别")
            movie['category']=info
        elif info.startswith("◎豆瓣评分"):
            info=parse_info(info,"◎豆瓣评分")
            movie['douban_rating']=info
        elif info.startswith("◎片　　长"):
            info=parse_info(info,"◎片　　长")
            movie['duration']=info
        elif info.startswith("◎导　　演"):
            info = parse_info(info, "◎导　　演")
            movie['director'] = info
        elif info.startswith("◎主　　演"):
            info = parse_info(info, "◎主　　演")
            actors = [info]
            for x in range(index + 1, len(infos)):
                actor = infos[x].strip()
                if actor.startswith("◎"):
                    break
                actors.append(actor)
            movie['actors'] = actors
        elif info.startswith("◎简　　介"):
            info = parse_info(info, "◎简　　介")
            movie['profile']=infos[index+1].strip()
    imgs=content.xpath(".//img/@src")
    movie['img_url']=imgs[0]
    download_url = html.xpath("//td[@bgcolor='#fdfddf']/a/@href")
    movie['download_url'] = download_url
    return movie


def spider():
    urls = Film_urls()
    movies=[]
    for url in urls[:10]:
        print("正在爬取电影详细内容。。。")
        movie=Film_content(url)
        movies.append(movie)
    return movies

if __name__ == '__main__':
    movies=spider()
    print(movies)