爬虫---requests的基本使用之练习项目

requests的使用练习项目：

建议可以先学习urllib库，再来学习requests更加的容易理解

写一下代码之前不要忘记下载第三方库哦~
在Terminal中输入：

pip install requests

项目（一）壁纸爬取

import requests
from lxml import etree
import time
import os


# 1.获取彼岸桌面url链接地址
def get_url():
    url_list = ['http://www.netbian.com/index.htm']
    for i in range(2,5):
        url_list.append(f'http://www.netbian.com/index_{i}.htm')
    return url_list
# url_list = get_url()
# print(url_list)


# 2.发起响应
def get_response(url):
    time.sleep(0.5)
    response = requests.get(url)
    content = response.content
    return content


# 3.获取数据列表  提取投票url地址和图片名
def get_content(content):
    html_str = etree.HTML(content.decode('gbk'))
    content_list = []
    li_list = html_str.xpath(".//div[@class='list']/ul/li")
    for li in li_list:
        item = {}
        item['name'] = li.xpath('./a/b/text()')
        item['img_href'] = li.xpath('./a/img/@src')
        if item['name']:
            content_list.append(item)
    return content_list


# 4.下载并保存图片
def download_img(content_list):
    for content in content_list:
        img_name = content['name'][0]
        path_img = './img'
        if os.path.exists(path_img):
            pass
        else:
            os.mkdir(path_img)
        with open(path_img+f"/{img_name}.jpg","wb") as f:
            f.write(get_response(content['img_href'][0]))
            print(img_name+'下载成功')


# 5.运行函数
def run():
    url_list = get_url()
    for url in url_list:
        content = get_response(url)
        content_list = get_content(content)
        download_img(content_list)


if __name__ == '__main__':
    run()

项目（二）图片爬取

import requests
from bs4 import BeautifulSoup
from urllib import parse
import os


class Skin(object):
    def __init__(self):
        # 王者荣耀皮肤英雄的json数据
        self.hero_url = 'https://pvp.qq.com/web201605/js/herolist.json'
        # 英雄详细页的通用url前缀信息
        self.base_url = 'https://pvp.qq.com/web201605/herodetail/'
        # 英雄详细页url后缀信息
        self.detail_url = ''
        # 图片存储文件夹
        self.img_folder = 'skin'
        # 图片url的通用前缀
        self.skin_url = 'https://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/'
        # 图片url的后缀信息
        self.skin_detail_url = ''

    def get_hero(self):
        """获取英雄的json数据"""
        request = requests.get(self.hero_url)
        # Requests中内置一个JSON解码器，可处理JSON数据返回成字典
        hero_list = request.json()
        return hero_list

    def get_hero_skin(self, hero_name, hero_no):
        """获取详细页英雄皮肤展示的信息，并爬图"""
        url = parse.urljoin(self.base_url, self.detail_url)
        request = requests.get(url)
        request.encoding = 'gbk'
        html = request.text
        # 获取皮肤信息的节点
        soup = BeautifulSoup(html, 'lxml')
        skip_list = soup.select('.pic-pf-list3')
        for skin_info in skip_list:
            # 获取皮肤名称
            img_names = skin_info.attrs['data-imgname']
            name_list = img_names.split('|')
            skin_no = 1
            # 循环下载皮肤图片
            for skin_name in name_list:
                self.skin_detail_url = '%s/%s-bigskin-%s.jpg' % (hero_no, hero_no, skin_no)
                skin_no += 1
                img_name = hero_name + '-' + skin_name + '.jpg'
                self.download_skin(img_name)

    def download_skin(self, img_name):
        """下载皮肤图片"""
        img_url = parse.urljoin(self.skin_url, self.skin_detail_url)
        request = requests.get(img_url)
        if request.status_code == 200:
            print('download-%s' % img_name)
            img_path = os.path.join(self.img_folder, img_name)
            #用来打开本地文件，会在使用完毕后，自动关闭文件，无需手动书写close()
            #‘wb’：表示以二进制写方式打开，只能写文件， 如果文件不存在，创建该文件；如果文件已存在，则覆盖写
            with open(img_path, 'wb') as img:
                img.write(request.content)
        else:
            print('img error!')

    def make_folder(self):
        """创建图片存储文件夹"""
        if not os.path.exists(self.img_folder):
            os.mkdir(self.img_folder)

    def run(self):
        """脚本执行入口"""
        self.make_folder()
        hero_list = self.get_hero()
        for hero in hero_list:
            hero_no = str(hero['ename'])
            self.detail_url = hero_no + '.shtml'
            hero_name = hero['cname']
            self.get_hero_skin(hero_name, hero_no)


# 程序执行入口
if __name__ == '__main__':
    skin = Skin()
    skin.run()