python学习 - day5

1、图片的下载

# 图片的下载
import requests
url = 'http://www.hinews.cn/pic/003/005/430/00300543000_b6551f10.jpg'
response = requests.get(url)
# 获取bytes类型的响应
data = response.content
with open('lixian.jpg', 'wb') as f:
    f.write(data)

结果：

李现

2、豆瓣TOP250电影排行爬虫

• 解决 “from lxml import etree”导入时etree标红问题：

from lxml import html
etree = html.etree

• 爬虫爬排行榜信息并下载电影封面

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"}
    # 根据url地址栏的页面start=?规律设置步长
    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
            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)
            # 电影的名字
            # movie_name
            movie_name = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="hd"]/a/span[1]/text()')[0]
            # print(movie_name)
            # 电影的介绍
            # movie_intro
            movie_intro = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')[0].strip()
            # print(movie_intro)
            # 电影的星级
            # star
            star = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[2]/text()')[0]
            # print(star)
            # 电影的评价
            # evaluate
            evaluate = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
            evaluate = evaluate[0].replace('人评价', '')
            # print(evaluate)
            # 电影的描述
            # describe
            describe = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span[1]/text()')
            # print(describe)
            # 电影封面地址
            # movie_img_path
            movie_img_path = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
            # print(movie_img_path)

            movie_list_info.append({
                'serial_number': serial_number,
                'movie_name': movie_name,
                'movie_intro': movie_intro,
                'star': star,
                'evaluate': evaluate,
                'describe': describe,
                'movie_img_path': movie_img_path
            })
    for movie in movie_list_info:
        print(movie)

   # 下载图片
    for movie in movie_list_info:
        # 获取图片地址
        url = movie['movie_img_path']
        resp = requests.get(url)
        # 如果请求成功
        if resp.status_code == 200:
            # 图片文件名字以排行序号命名
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./imgs/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)
spider_douban_top250()

结果：

电影封面图片