프로젝트 _1

from urllib.request import urlopen
from bs4 import BeautifulSoup
import pprint as ppr
import requests
from urllib import request
import os
class URL_Parser:
    def __init__(self):
        self.html_string = ""           # type string
        self.html = None
        self.bs4Object = None
        self.tag_name_list = list()     # type list
        self.urlSub = list()            # type list
        self.search_Color_List = list() # type list
    # func(1)
    def step1(self, html):
        self.html_string = html
        self.html = urlopen(self.html_string)
        self.bs4Object = BeautifulSoup(self.html, "html.parser")
        temp = self.bs4Object.find_all("div", {"class":"colordvcon"})
        #print ("type(temp) => {}".format(type(temp))) #=> <class 'bs4.element.ResultSet'>
        for t in temp:
            Tag_text = t.get_text().strip()
            #print ("type(Tag_text.get_text) => {}".format(type(Tag_text))) #=> <class 'str'>
            #print ("Tag_text.get_text() => {}".format(Tag_text)) #=> '#eceaea'
            self.tag_name_list.append(Tag_text[1:])
        #print (self.tag_name_list)

    # func(2)
    def step2(self):
        for element in self.tag_name_list:
            self.urlSub.append (self.html_string +"color/"+element)

    # func(3)
    def step3(self):
        for element in self.urlSub:
            print ("{}".format(element))
            t_html = urlopen(element)
            t_bsObject = BeautifulSoup(t_html, "html.parser")
            result = t_bsObject.find_all("div",{"class":"colordvconline"})
            for t in result:
                Tag_text = t.get_text().strip()
                self.search_Color_List.append(Tag_text)
                #print ("=====>  {}".format(Tag_text))
        #ppr.pprint(self.search_Color_List)

    # func(4)
    def step4(self):
        for i in range(0, len(self.search_Color_List)):
            data = self.search_Color_List[i]
            payload = {'q': data, 'oq': data}
            url = "https://www.google.co.kr/search?hl=ko&tbm=isch&source=hp&biw=1041&bih=781&ei=quxKWuidKca20QT9uJIo"
            html = requests.get(url, params=payload)
            s = html.text
            t = BeautifulSoup(s, 'html.parser')
            os.chdir("E:\\tst") # directory 이동
            d = "dir" + str(i+1)
            try:
                os.mkdir(d) # 파일 만들기
            except:
                print ("디렉토리가 이미 존재합니다.")
            else:
                print ("디렉토리 %s Success"%(d))
            os.chdir("E:\\tst\\" + d)
            sava_name_f = "img_" + str(i) +"_indx_num_"
            indx_num = 0
            for i in t.find_all('img'):
                #print (i['src'])
                Img_url = i['src']
                #print (Img_url)
                sava_name_f = sava_name_f + str(indx_num) + ".png"
                try:
                    mem = request.urlopen(Img_url).read()
                    with open(sava_name_f, mode="wb") as f:
                        f.write(mem)
                except:
                    print ("error")
                else:
                    print ("success save")
                indx_num += 1
            #     try:
            #         Img_url = i['src']
            #         sava_name_f = "test.png"
            #     except:
            #         print ("error")
            #     else:
            #         mem = request.urlopen(Img_url).read()
            #         with open(sava_name_f, mode="wb") as f:
            #             f.write(mem)
            #             print("저장 되었습니다.")

def main():
    m_url_object = URL_Parser() # 객체 생성
    m_url_object.step1('http://www.color-hex.com/') # argument : url
    m_url_object.step2()
    m_url_object.step3()
    m_url_object.step4()

if __name__ == "__main__":
    main()