爬虫11-爬取复杂网页，电影天堂

Posted 2021-03-06 wcymiracle

import requests
from  lxml import  etree
url_domain="https://www.dytt8.net"
headers={
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/65.0.3325.181 Safari/537.36"
}
def get_detail_urls(url):
    response=requests.get(url,headers=headers)
    text =response.content.decode(‘gbk‘, "ignore")

    html=etree.HTML(text)
    detail_urls=html.xpath("//table[@class=‘tbspan‘]//a[2]/@href")
    detail_urls=map(lambda url:url_domain+url,detail_urls)
    return detail_urls

def parse_info(info,rule):
    return info.replace(rule, "").strip()

def parse_detail_url(url="https://www.dytt8.net/html/gndy/dyzz/20200306/59787.html"):
    movie={}
    response=requests.get(url,headers=headers)
    text=response.content.decode("gbk","ignore")
    html=etree.HTML(text)
    title=html.xpath("//div[@class=‘title_all‘]//font[@color=‘#07519a‘]//text()")[0]
    movie[‘title‘]=title
    zoomE=html.xpath("//div[@id=‘Zoom‘]")[0]
    infos=zoomE.xpath("//text()")
    for index,info in enumerate(infos):
        if 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("◎上映日期"):
            info = parse_info(info, "◎上映日期")
            movie[‘date‘] = info
        elif info.startswith("◎片　　长"):
            info = parse_info(info, "◎片　　长")
            movie[‘time‘] = info
        elif info.startswith("◎豆瓣评分"):
            info = parse_info(info, "◎豆瓣评分")
            movie[‘score‘] = 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
    return movie

def spider():
    base_url="https://www.dytt8.net/html/gndy/dyzz/list_23_{}.html"
    movies=[]
    for x in range(1,8):
        url=base_url.format(x)
        detail_urls=get_detail_urls(url)
        for detail_url in detail_urls:
            movie=parse_detail_url(detail_url)
            movies.append(movie)
            print(movie)

if __name__ == ‘__main__‘:
    spider()