21天打造分布式爬蟲-豆瓣電影和電影天堂實戰（三）

3.1.豆瓣電影

使用lxml

import requests
from lxml import etree

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
    'Referer':'https://movie.douban.com/'
}
url = 'https://movie.douban.com/cinema/nowplaying/beijing/'
response = requests.get(url,headers=headers)
text = response.text

html = etree.HTML(text)
#獲取正在上映的電影
ul = html.xpath("//ul[@class='lists']")[0]
lis = ul.xpath("./li")
movies = []

for li in lis:
    title = li.xpath("@data-title")[0]
    score = li.xpath("@data-score")[0]
    duration = li.xpath("@data-duration")[0]
    region = li.xpath("@data-region")[0]
    director = li.xpath("@data-director")[0]
    actors = li.xpath("@data-actors")[0]
    #電影海報圖片
    thumbnail = li.xpath(".//img/@src")[0]

    movie = {
        'title':title,
        'score':score,
        'duration':duration,
        'region':region,
        'director':director,
        'actors':actors,
        'thumbnail':thumbnail,
    }
    movies.append(movie)

print(movies)

 3.2.電影天堂

使用lxml

import requests
from lxml import etree

BASE_DOMAIN = 'http://dytt8.net'

HEADERS = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
}

def get_detail_urls(url):
    '''獲取詳情頁url'''
    response = requests.get(url, headers=HEADERS)
    text = response.text
    html = etree.HTML(text)
    # 獲取電影詳情的url
    detail_urls = html.xpath("//table[@class='tbspan']//a/@href")
    #加上域名，拼接成完整的url
    detail_urls = map(lambda url:BASE_DOMAIN + url,detail_urls)
    return detail_urls

def parse_detail_page(url):
    '''處理爬取頁面'''
    movie = {}
    response= requests.get(url,headers=HEADERS)
    text = response.content.decode('gbk')
    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]
    imgs = zoomE.xpath(".//img/@src")
    cover = imgs[0]         #電影海報
    movie['cover'] = cover
    #因為有的電影沒有截圖，所有這里加個異常處理
    try:
        screenshot = imgs[1]    #電影截圖
        movie['screenshot'] = screenshot
    except IndexError:
        pass

    infos = zoomE.xpath(".//text()")
    for index,info in enumerate(infos):
        if info.startswith("◎年　　代"):
            info = info.replace("◎年　　代","").strip()
            movie['year'] = info
        elif info.startswith("◎產　　地"):
            info = info.replace("◎產　　地", "").strip()
            movie['country'] = info
        elif info.startswith("◎類　　別"):
            info = info.replace("◎類　　別", "").strip()
            movie['category'] = info
        elif info.startswith("◎豆瓣評分"):
            info = info.replace("◎豆瓣評分", "").strip()
            movie['douban_rating'] = info
        elif info.startswith("◎片　　長"):
            info = info.replace("◎片　　長", "").strip()
            movie['duration'] = info
        elif info.startswith("◎導　　演"):
            info = info.replace("◎導　　演", "").strip()
            movie['director'] = info
        
        #影片的主演有多個，所有要添加判斷
        elif info.startswith("◎主　　演"):
            info = info.replace("◎主　　演", "").strip()
            actors = [info,]
            for x in range(index+1,len(infos)):
                actor = infos[x].strip()
                if actor.startswith("◎簡　　介 "):
                    break
                actors.append(actor)
            # print(actors)
            movie['actors'] = actors

        elif info.startswith("◎簡　　介 "):
            info = info.replace("◎簡　　介 ", "").strip()
            for x in range(index+1,len(infos)):
                profile = infos[x].strip()
                if profile.startswith("【下載地址】"):
                    break
                # print(profile)
                movie['profile'] = profile
    #下載地址
    download_url = html.xpath("//td[@bgcolor='#fdfddf']/a/@href")[0]
    # print(download_url)
    movie['download_url'] = download_url
    return movie

def spider():
    base_url = 'http://dytt8.net/html/gndy/dyzz/list_23_{}.html'
    movies = []
    for x in range(1,8):    #爬前7頁
        url = base_url.format(x)
        detail_urls = get_detail_urls(url)
        for detail_url in detail_urls:
            movie = parse_detail_page(detail_url)      
            movies.append(movie)
            print(movie)
    print(movies)    #所有的電影信息

if __name__ == '__main__':
    spider()