一、图片下载

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

python.png

二、豆瓣top250爬虫，并下载封面图

# 导入
import requests
from lxml import 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"}
    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()')
            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()')[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()')[
                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()')[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()')
            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()')
            # print(describe)
            # 电影封面的地址
            movie_img_url = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
            # print(movie_img_url)

            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)
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./imgs/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)

spider_douban_top250()

二、酷狗爬虫，下载音乐

import re
import json
import time
import requests
from fake_useragent import UserAgent
ua = UserAgent()
def get_song(song_name):
    search_url = "https://songsearch.kugou.com/song_search_v2?callback=jQuery112405132987859127838_1550204317910&page" \
                 "=1&pagesize=30&userid=-1&clientver=&platform=WebFilter&tag=em&filter=2&iscorrection=1&privilege_fil" \
                 "ter=0&_=1550204317912&keyword={}".format(song_name)
    headers1 = {
        "UserAgent": ua.random
    }
    headers2 = {
        "Cookie": "kg_mid=3786e26250f01bf2c64bc515820d9752; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1559960644; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1559960644; ACK_SERVER_10015=%7B%22list%22%3A%5B%5B%22bjlogin-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10016=%7B%22list%22%3A%5B%5B%22bjreg-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10017=%7B%22list%22%3A%5B%5B%22bjverifycode.service.kugou.com%22%5D%5D%7D; kg_dfid=0iEqIA1uep0h0AogH30Jq1Od; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e",
        "Host": "www.kugou.com",
        "Referer": "http://www.kugou.com/",
        "UserAgent": ua.random
    }
    res = requests.get(search_url, headers=headers1)
    # print(res.text)
    start = re.search("jQuery\d+_\d+\(?", res.text)
    js = json.loads(res.text.strip().lstrip(start.group()).rstrip(")"))  # 末尾有一个换行需要去掉
    song_list = js['data']['lists']

    for i in range(10):
        print(str(i + 1) + ">>>" + str(song_list[i]['FileName']).replace('<em>', '').replace('</em>', ''))
    num = int(input("\n请输入您想要下载的歌曲序号："))
    print("请稍等，下载歌曲中...")
    time.sleep(1)

    file_hash = song_list[num - 1]['FileHash']

    hash_url = "http://www.kugou.com/yy/index.php?r=play/getdata&hash={}".format(file_hash)
    # print(hash_url)
    hash_res = requests.get(hash_url, headers=headers2)
    hash_js = hash_res.json()  # json格式
    # print(hash_js)
    play_url = hash_js['data']['play_url']

    # 下载歌曲
    try:
        with open("music/" + song_name + ".mp3", "wb")as fp:
            fp.write(requests.get(play_url).content)
        print("歌曲已下载完成！")
    except Exception as e:
        print(e)

if __name__ == '__main__':
    get_song(input("请输入您想要搜索的歌曲名称："))