import requests
from bs4 import BeautifulSoup
import re
import os
import json
import sys

downsize = 512
geturl = "https://www.veryicon.com/icons/healthcate-medical/medical-icon-two-color-icon"

baseurl = "https://www.veryicon.com"

headers = {
			#"referer": geturl,
           "user-agent": "Mozilla/5.0 (Windows NT 10.0; "
                         "Win64; x64) AppleWebKit/537.36 "
                         "(KHTML, like Gecko) Chrome/95.0.4638.54 "
                         "Safari/537.36 Edg/95.0.1020.40"}

save_path = "./savepic/"


def getHtml(url, headers=headers):
	try:
		r = requests.get(url, headers=headers)
		#r.raise_for_status()
		r.encoding = "utf-8"
		return r
	except BaseException:
		print("获取失败")
		
def getHtmlCode(url):
	try:
		r1 = requests.get(url,'lxml')
		#r1.raise_for_status()
		r1.encoding='utf-8'
		return r1
	except BaseException:
		print("获取失败")
	
def savefile(url,filename):
	#print(url)
	#h_split = url.split('/')
	#filename = h_split[len(h_split)-1]
	picture = getHtml(url)
	#print(dir(picture))
	#print(picture.__attrs__)
	#print(picture.__bool__)
	#print(picture.__class__)
	#print(picture.__delattr__)
	#print(picture.__dict__)
	#print(picture.__dir__)
	#print(picture.__doc__)
	#print(picture.__enter__)
	#print(picture.__eq__)
	#print(picture.__exit__)
	#print(picture.__format__)
	#print(picture.__ge__)
	#print(picture.__getattribute__)
	#print(picture.__getstate__)
	#print(picture.__gt__)
	#print(picture.__hash__)
	#print(picture.__init__)
	#print(picture.__init_subclass__)
	#print(picture.__iter__)
	#print(picture.__le__)
	#print(picture.__lt__)
	#print(picture.__module__)
	#print(picture.__ne__)
	#print(picture.__new__)
	#print(picture.__nonzero__)
	#print(picture.__reduce__)
	#print(picture.__reduce_ex__)
	#print(picture.__setattr__)
	#print(picture.__setstate__)
	#print(picture.__sizeof__)
	#print(picture.__str__)
	#print(picture.__subclasshook__)
	#print(picture.__weakref__)
	#print(picture._content)
	#print(picture._content_consumed)
	#print(picture._next)
	#print(picture.apparent_encoding)
	#print(picture.close)
	#print(picture.connection)
	#print(picture.content)
	#print(picture.cookies)
	#print(picture.elapsed)
	#print(picture.encoding)
	#print(picture.headers)
	#print(picture.history)
	#print(picture.is_permanent_redirect)
	#print(picture.is_redirect)
	#print(picture.iter_content)
	#print(picture.iter_lines)
	#print(picture.json)
	#print(picture.links)
	#print(picture.next)
	#print(picture.ok)
	#print(picture.raise_for_status)
	#print(picture.raw)
	#print(picture.reason)
	#print(picture.request)
	#print(picture.status_code)
	#print(picture.text)
	#print(picture.url)
	
	#print(dir(picture))
	#sys.exit()
	if not os.path.exists(save_path):
		os.makedirs(save_path)
	with open(save_path+filename,"wb") as f:
		f.write(picture.content)
	print(filename+"下载完毕")
	picture.close()
	
def parserHtml(url):
	herflist = []
	r = getHtmlCode(url)
	soup = BeautifulSoup(r.text,"html.parser")
	pages = soup.find(name='div', class_='pager')
	if pages==None :
		herflist = herflist + getonepage(soup)
	else :
		numlist = pages.find(name='a')
		mxnum = int(max(numlist.text))
		num = 1
		while num <= mxnum:
			r001 = getHtmlCode(url+"/"+str(num))
			soup001 = BeautifulSoup(r001.text,"html.parser")
			herflist = herflist + getonepage(soup001)
			r001.close()
			num = num + 1
	r.close()
	return herflist

def getonepage(bs4_soup):
	herflist = []
	#soup = BeautifulSoup(htmltext,"html.parser")
	soup = bs4_soup
	icons = soup.find(name='div', id='sider-left')
	icons_items = icons.find_all(name='a')
	for icon_one in icons_items:
		#print(icon_one)
		if icon_one.parent.name == 'h4':
			herflist.append((icon_one.attrs["href"],icon_one.attrs["title"]))
	return herflist

def downimg(href,filename):
	r = getHtmlCode(baseurl + href)
	soup = BeautifulSoup(r.text,"html.parser")
	filename = filename.replace(' ' , '_')
	filename = filename.replace(',' , '_')
	filename = filename.replace('__' , '_')
	filename = filename.replace("'" , '')
	filename = filename.replace("?" , '')
	h_split = href.split('/')
	filename1 = h_split[len(h_split)-1]
	filename1 = filename1.split('.')
	filename = filename1[0]
	if not os.path.exists(save_path+filename + "_"+str(downsize)+".png"):
		png_data = soup.find(name='div', class_='sub-downloads')
		png_items = png_data.find_all(name='a')
		for png_dow in png_items:
			add_name = png_dow.text
			add_name = add_name.replace('PNG ' , '')
			add_name = add_name.replace('px' , '')
			if int(add_name)==downsize :
				if png_dow.attrs["href"][0:2] == "//":
					savefile("https:"+png_dow.attrs["href"],filename+"_"+add_name + ".png")
				else:
					savefile(baseurl + png_dow.attrs["href"],filename+"_"+add_name + ".png")

def main():
	if not os.path.exists(save_path+"task_down.json"):
		herflist = parserHtml(geturl)
		task_down = json.dumps(herflist)
		if not os.path.exists(save_path):
			os.makedirs(save_path)
		with open(save_path+"task_down.json","w") as f:
			f.write(task_down)
	else :
		file_obj = open(save_path+"task_down.json",'r') 
		try:
			task_down = file_obj.read()
			herflist = json.loads(task_down)
		finally:
			file_obj.close()
	
	#print(herflist)
	for herf,filename in herflist:
		downimg(herf,filename)

main()

有些分类文件过多，无法一次全部下载成功，所以增加了本地缓存记录和对比下载代码：

#此部分将下载的图片列表页面缓存到本地JSON文件，本地有文件则载入数据
if not os.path.exists(save_path+"task_down.json"):
		herflist = parserHtml(geturl)
		task_down = json.dumps(herflist)
		if not os.path.exists(save_path):
			os.makedirs(save_path)
		with open(save_path+"task_down.json","w") as f:
			f.write(task_down)
	else :
		file_obj = open(save_path+"task_down.json",'r') 
		try:
			task_down = file_obj.read()
			herflist = json.loads(task_down)
		finally:
			file_obj.close()

以下是判读本地是否已经有图片文件，没有则下载：

if not os.path.exists(save_path+filename + "_512.png"):
		png_data = soup.find(name='div', class_='sub-downloads')
		png_items = png_data.find_all(name='a')
		for png_dow in png_items:
			add_name = png_dow.text
			add_name = add_name.replace('PNG ' , '')
			add_name = add_name.replace('px' , '')
			if int(add_name)==512 :
				savefile(baseurl + png_dow.attrs["href"],filename+"_"+add_name + ".png")