基础知识

1）实现分页爬虫

for i in range(0,250,25):
url= 'https://movie.douban.com/top250?start={}&filter='.format(i)
循环访问网址不同的start的值就是不同的访问页，其他的爬虫过程类似昨天的。

Python例子

一、在网上下载图片

◉ 代码

import requests
response = requests.get('http://g.hiphotos.baidu.com/image/pic/item/5366d0160924ab18014cefd83bfae6cd7a890b82.jpg')
# #获取Bytes类型的响应
data = response.content
with open('./python.png','wb') as f:
    f.write(data)

◉ 结果截图

豆瓣TOP10爬虫

▶ 要求：
（1）获取：电影序号，电影名，电影介绍，电影星级，电影评价，电影描述，电影封面图地址
（2）输出所有的数据
（3）将所有的封面图片下载下来
▶ 代码：

#豆瓣TOP250爬虫
#导入
import requests
from lxml import etree
def spider_douban_top250():
    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)
        #获取bytes类型的响应
        data = requests.get(url,headers = headers).content
        html = etree.HTML(data)
        ol_list = html.xpath('//div[@id="content"]/div/div[1]/ol/li')

       
        movies_info = []
        for movie in ol_list:
            #影片序号
            serial_number = movie.xpath('./div/div[@class="pic"]/em/text()')
            if len(serial_number) == 0:
                serial_number = ''
            else:
                serial_number = serial_number[0]
            # print(serial_number)

            #电影的名字
            movies_name = movie.xpath('div/div[@class="info"]/div[@class="hd"]/a/span[1]/text()')
            if len(movies_name) == 0:
                movies_name = ''
            else:
                movies_name = movies_name[0]
            # print(movies_name)

            #电影介绍     只能用于字典.strip() 用来去空格
            movie_introduce = movie.xpath('div/div[@class="info"]/div[@class="bd"]/p/text()')
            if len(movie_introduce) == 0:
                movie_introduce = ''
            else:
                movie_introduce = movie_introduce[0].strip()
            # print(movie_introduce)

            #电影星级
            star = movie.xpath('div/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[@class="rating_num"]/text()')
            if len(star) == 0:
                star = ''
            else:
                star = star[0]
            # print(star)

            #电影评价
            evalute = movie.xpath('div/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')

            if len(evalute) == 0:
                evalute = ""
            else:
                evalute = evalute[0]
            evalute = evalute.replace('人评价', '')
            # print(evalute)

            #电影描述
            describe = movie.xpath('div/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[@class="inq"]/text()')
            if len(describe) == 0:
                describe = ''
            else:
                describe = describe[0]
            # print(describe)

            #电影封面地址
            movie_img_url = movie.xpath('div/div[@class="pic"]/a/img/@src')
            if len(movie_img_url) == 0:
                movie_img_url = ''
            else:
                movie_img_url = movie_img_url[0]
            # print(movie_img_url)

            movies_info.append({
                'serial_number':serial_number,
                'movies_name':movies_name,
                'movie_introduce':movie_introduce,
                'star':star,
                'evalute':evalute,
                'describe':describe,
                'movie_img_url':movie_img_url
            })

        # print("这是第{}个页面".format(i))
        #遍历
        for movie in movies_info:
            print(movie)

        #下载图片
        for movie in movies_info:
            url = movie['movie_img_url']
            resp = requests.get(url)
            if resp.status_code == 200:
                img_name = 'hml00{}.jpg'.format(movie['serial_number'])
                with open('./imgs/{}'.format(img_name),'wb') as f:
                    f.write(resp.content)
            else:
                print("图片下载失败！")
    print("成功！")
spider_douban_top250()

▶ 数据截图
数据太多，这里就放部分数据。

▶ 项目截图