豆瓣Top250電影信息提取、圖片下載

• 導入

import requests
from lxml import etree
# 某些版本使用
# from lxml import html
# etree = html.etree

• 方法

def spider_douban_top250():
    movie_list_info = []
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
    for i in range(0, 250, 25):
        url = 'https://movie.douban.com/top250?start={}&filter='.format(i)
        # 獲取bytes類型響應
        data = requests.get(url, headers=headers).content
        html = etree.HTML(data)
        ol_list = html.xpath('//div[@id="content"]//div[@class="article"]/ol/li')
        for movie in ol_list:
            # 影片序號
            serial_number = movie.xpath('./div[@class="item"]/div[@class="pic"]/em/text()')
            if len(serial_number) == 0:
                serial_number = ''
            else:
                serial_number = serial_number[0]
            # print(serial_number)
            # 電影的名字
            movie_name = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="hd"]/a/span[1]/text()')[0]
            # print(movie_name)
            # 電影的介紹
            movie_introduce = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')[0].strip()
            # print(movie_introduce)
            # 電影的星級
            star = \
                movie.xpath(
                    './div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[2]/text()')[0]
            # print(star)
            # 電影的評價
            evalute = movie.xpath(
                './div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
            evalute = evalute[0].replace('人評價', '')
            # print(evalute)
            # 電影的描述
            describe = movie.xpath(
                './div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[1]/text()')
            # print(describe)
            # 電影封面的地址
            movie_img_url = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
            # print(movie_img_url)
            # 添加
            movie_list_info.append({
                'serial_number': serial_number,
                'movie_name': movie_name,
                'movie_introduce': movie_introduce,
                'star': star,
                'evalute': evalute,
                'describe': describe,
                'movie_img_url': movie_img_url
            })
            # 遍歷
    for movie in movie_list_info:
        print(movie)
        # 下載圖片
    for movie in movie_list_info:
        url = movie['movie_img_url']
        resp = requests.get(url)
        # 運行狀態(tài)
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./image/{}'.format(img_name), 'wb') as f:
                # 寫入
                f.write(resp.content)

spider_douban_top250()