python---表情包爬取

python—表情包爬取

闲着无聊时写了一个表情包爬取的简单脚本

运行效果如下

• 输入要爬取的页数以及要保存的目录地址
  
• 坐等表情包
• 运行后效果如下
  

代码如下

import requests
from bs4 import BeautifulSoup
import os
global headers

#请求头
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3754.400 QQBrowser/10.5.4020.400'}

#初始网页爬取
def get_page(url):
	item_list = []
	response = requests.get(url, headers=headers, timeout=(3, 3)).text
	soup = BeautifulSoup(response, 'lxml')
	soup.prettify()
	data = soup.select('#home > div > div.col-sm-9.center-wrap > a')
	for item in data:
		item_list.append({'title' : item.select('.random_title')[0].get_text(), 'href' : item['href']})
	return item_list
#图片链接获取
def get_href(item_list,dizhi):
	for item in item_list:
		img_list=[]
		if not os.path.exists('{}/{}'.format(dizhi, item['title'])):
			os.mkdir('{}/{}'.format(dizhi,item['title']))
		address='{}/{}'.format(dizhi,item['title'])
		print(address)
		url=item['href']
		response=requests.get(url,headers=headers, timeout=(3, 3)).text
		soup=BeautifulSoup(response,'lxml')
		soup.prettify()
		imgs=soup.select('body > div.container_ > div.container > div > div.col-sm-9.center-wrap > li > div.pic-content > div > table > tbody > tr:nth-child(1) > td > a > img')
		num = 1
		for img in imgs:
			if img['alt'] == '':
				img['alt'] = str(num)
			img_list.append({'name' : img['alt'], 'url' : img['src']})
			num+=1
		# print(img_list)
		#download
		for img in img_list:
			try:
				down_img(img['url'], address, img['name'])
			except :
				continue
#图片下载
def down_img(url,address,name):
	img=requests.get(url, headers=headers, timeout=(3, 3)).content
	dress=address+'/'+name+'.jpg'
	print('正在下载...')
	print(dress)
	if not os.path.exists(dress):
		with open(dress,'wb') as sub:
			sub.write(img)
	print('OK')
def main():
	page=int(input('请输入要下载的页数 ：'))
	dizhi=input('请输入要下载的地址（C:/Users/KYA08/Desktop/表情包）可以桌面创建表情包文件夹，然后复制前面路径做简单修改：')
	for page in range(1,page):
		url='https://www.doutula.com/article/list/?page={}'.format(page)
		# items = get_page(url)
		# get_href(items, dizhi)
		try:
			items = get_page(url)
			get_href(items, dizhi)
		except Exception as e:
			continue

if __name__ == '__main__':
	main()

可自行打包

方式如下

1. 进入此py文件所在的文件夹
2. 在文件路径框内输入 cmd，回车即可进入当下目录的命令行窗口

3.进入命令行窗口后输入以下命令：
pyinstaller -F demo.py
注： demo,py替换为py文件名
4. 即可在当前文件夹下生成dist文件夹，里面即为打包后的可执行文件

说明

• 爬取网站为随机找的表情包网站，不含恶意
• 整体代码不够完善，一些空外目录未处理，速度未做提升，主要为基本操作代码，大佬勿喷，本人小白