python爬虫——图片下载

import requests
response=requests.get('https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1564640268773&di=90d3bdcd271057766ce22862c2c3b77e&imgtype=0&src=http%3A%2F%2Fmelbournemakerspace.org%2Fblog%2Fwp-content%2Fuploads%2F2015%2F04%2FPython.png')
#获取bytes的类型的响应
data=response.content
with open('python.png','wb') as f:
    f.write(data)

python爬虫——分页、批量图片下载

• 爬虫分页 —— 用循环实现，用循环的步长
• 储存图片
• etree报红 ——新版本无法直接from lxml import etree这样，但是它只不过是换了一个办法引出etree模块
• etree报红也是可以运行的
• 可以用from lxml import html 换行 etree=html.etree 可以解决报红

# 导入
import requests
from lxml import html
etree=html.etree

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"}

    # 用于分页的操作
    # 循环 步长25 页面显示25 对每一页进行循环

    for i in range(0, 250, 25):
        url = 'https://movie.douban.com/top250?start={}&filter='.format(i)

        # 获取bytes类型响应
        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:

            # 影片序号
            serial_number = movie.xpath('./div[@class="item"]/div[@class="pic"]/em/text()')
            #简单的抛出异常操作，减少报错
            if len(serial_number) == 0:
                serial_number = ''
            else:
                serial_number = serial_number[0]
            # print(serial_number)

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

            # 电影的介绍
            movie_introduce = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')
            if len(movie_introduce) == 0:
                movie_introduce = ''
            else:
                movie_introduce = movie_introduce[0].strip()
            # print(movie_introduce)

            # 电影的星级
            star = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[2]/text()')
            if len(star) == 0:
                star = ''
            else:
                star = star[0]
            # print(star)

            # 电影的评价
            evalute = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
            if len(evalute) == 0:
                evalute = ''
            else:
                evalute = evalute[0].replace('人评价', '')
            # print(evalute)

            # 电影的描述
            describe = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[1]/text()')
            if len(describe) == 0:
                describe = ''
            else:
                describe = describe[0]
            # print(describe)

            # 电影封面的地址
            movie_img_url = movie.xpath('./div[@class="item"]/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)

            # 将信息储存
            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
            })

    # for movie in movie_list_info:
    #     print(movie)

        # 下载图片
    for movie in movie_list_info:
        url = movie['movie_img_url']
        resp = requests.get(url)
        # 获取状态码
        # 当状态码等于200时可以进行下面的操作
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./img/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)
spider_douban_top250()