# Time: 2020/05/08
#Author: Xiaohong
# 運行環境: OS: Windows 7
# Python: 3.7
# 功能: 根據關鍵詞 key 到baidu 下載 pic_number 張的圖片
# https://www.jianshu.com/p/33bee611fa7d
# https://www.cnblogs.com/SeekHit/p/6284974.html
主界面如下:
主界面對應的程式如下:
# -*- coding:utf-8 -*-
import tkinter as tk
from tkinter.ttk import *
from tkinter import ttk
from Tl_class_frame import *
# from Tl_baidu_DownPic02 import *
from Tl_baidu_DownPic02 import *
import tkinter.messagebox
import os
import time
from tkinter.filedialog import askopenfilename
class Tl_baidu_DownPic02_screen(object):
#設計UI 界面
def setupUI(self):
v = View(self.root, kind='日', orient=tk.HORIZONTAL)
v.v1['height'] = 120
# 設立LabelFrame
lf1=tk.LabelFrame(v.v1,text='參數')
lf1.pack(side=tk.LEFT,ipadx=60,ipady=20)
# #增加Label,用來
tk.Label(lf1,text='要下載在內容').pack(anchor=tk.NW)
self.keyword=tk.StringVar()
tk.Entry(lf1,width=50,textvariable=self.keyword).pack(anchor=tk.NW,expand='true',fill='x')
# lf1_2=tk.LabelFrame(lf1,text='文件夾路徑:')
lf1_2=tk.Frame(lf1)
lf1_2.pack(anchor=tk.NW,ipadx=60,ipady=10,padx=5)
# tk.Label(lf1_2,text='文件夾路徑:').pack(side=tk.LEFT)
tk.Label(lf1_2,text='文件夾路徑:').pack(anchor=tk.NW)
self.file1=tk.StringVar()
tk.Entry(lf1_2,width=40,textvariable=self.file1).pack(anchor=tk.NW)
vButton = tk.Button(lf1_2, text='...', width=3,command=self.getfile)
# vButton.pack(side=tk.LEFT)
vButton.pack(anchor=tk.NW)
tk.Label(lf1,text='所需圖片數量:').pack(anchor=tk.NW)
self.pic_number=tk.StringVar()
self.pic_number.set(10)
tk.Entry(lf1,width=10,textvariable=self.pic_number).pack(anchor=tk.NW)
vButton = tk.Button(lf1, text='下載1', width=8,command=self.Call_baidu_Downpic02)
vButton.pack(side=tk.LEFT)
def Call_baidu_Downpic02(self):
# print(self.keyword.get())
# print(self.file1.get())
# print(self.pic_number.get())
if self.keyword.get()=='' or self.file1.get()=='' or self.pic_number.get()=='':
# print('sssss')
tkinter.messagebox.showerror(title='操作失敗', message='有參數爲空,請先檢查')
else:
try:
pic_number1=int(self.pic_number.get())
call_DownPic02_main(self.keyword.get(),self.file1.get(),pic_number1)
tkinter.messagebox.showinfo(title='操作完成', message='操作完成')
except:
import sys
tuple=sys.exc_info()
errmsg='導入圖片失敗'+'錯誤爲:'+str(tuple[1])
tkinter.messagebox.showerror(title='操作失敗', message=errmsg)
def getfile(self):
xx = tk.filedialog.askdirectory()
self.file1.set(xx)
# 設立函數,來取得當前時間,作爲文件名的一部分,以免文件名重複
def get_sysdate2(self):
now = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime(time.time()))
# print(now)
return now
def setCenter(self,root, w, h):
ws = root.winfo_screenwidth()
hs = root.winfo_screenheight()
x = int((ws / 2) - (w / 2))
y = int((hs / 2) - (h / 2))
root.geometry('{}x{}+{}+{}'.format(w, h, x, y))
#類的運行主體
def __init__(self):
# self.root = tk.Tk() #本界面單獨運行時,需要用到本行語句
self.root = tk.Toplevel()
self.root.title(string='Baidu 圖片下載 管理')
self.setCenter(self.root, 700, 300)
self.setupUI()
self.root.mainloop()
if __name__=='__main__':
Tl_baidu_DownPic02_screen()
主程式如下:
import json
import itertools
import urllib
import requests
import os
import re
import sys
import time
# 設立函數,來取得當前時間,作爲文件名的一部分,以免文件名重複
def get_sysdate():
now = time.strftime("%m%d-%H%M%S", time.localtime(time.time()))
print(now)
return now
str_table = {
'_z2C$q': ':',
'_z&e3B': '.',
'AzdH3F': '/'
}
char_table = {
'w': 'a',
'k': 'b',
'v': 'c',
'1': 'd',
'j': 'e',
'u': 'f',
'2': 'g',
'i': 'h',
't': 'i',
'3': 'j',
'h': 'k',
's': 'l',
'4': 'm',
'g': 'n',
'5': 'o',
'r': 'p',
'q': 'q',
'6': 'r',
'f': 's',
'p': 't',
'7': 'u',
'e': 'v',
'o': 'w',
'8': '1',
'd': '2',
'n': '3',
'9': '4',
'c': '5',
'm': '6',
'0': '7',
'b': '8',
'l': '9',
'a': '0'
}
# str 的translate方法需要用單個字符的十進制unicode編碼作爲key
# value 中的數字會被當成十進制unicode編碼轉換成字符
# 也可以直接用字符串作爲value
char_table = {ord(key): ord(value) for key, value in char_table.items()}
# 解碼圖片URL
def decode(url):
# 先替換字符串
for key, value in str_table.items():
url = url.replace(key, value)
# 再替換剩下的字符
return url.translate(char_table)
# 生成網址列表
def buildUrls(word):
word = urllib.parse.quote(word) # 屏蔽特殊的字符、比如如果url裏面的空格!url裏面是不允許出現空格的
url = r"http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&fp=result&queryWord={word}&cl=2&lm=-1&ie=utf-8&oe=utf-8&st=-1&ic=0&word={word}&face=0&istype=2nc=1&pn={pn}&rn=60"
urls = (url.format(word=word, pn=x)
for x in itertools.count(start=0, step=60)) # itertools是python內置的模塊,count是生成無界限序列,從0開始,步長爲60,無限循環
return urls
# 解析JSON獲取圖片URL,
# 一個圖片對應許多鏈接,經測試圖片鏈接在 objURL 這個標籤內。用正則找出
# 括號表示分組,將括號的內容捕獲到分組當中
# 這個括號也就可以匹配網頁中圖片的url了
re_url = re.compile(r'"objURL":"(.*?)"') # 根據包含正則表達式的字符串創建模式對象
def resolveImgUrl(html):
imgUrls = [decode(x) for x in re_url.findall(html)]
# print(imgUrls)
return imgUrls
# for x in re_url.findall(html):
# print('aaa:')
# print(x)
# imgUrls=decode(x)
# print('bbb:')
# print(imgUrls)
# return imgUrls
def downImg(imgUrl, dirpath, imgName):
filename = os.path.join(dirpath, imgName)
try:
res = requests.get(imgUrl, timeout=15)
if str(res.status_code)[0] == "4":
# print(str(res.status_code), ":", imgUrl)
return False
except Exception as e:
print("拋出異常:", imgUrl)
print(e)
return False
with open(filename, "wb") as f:
f.write(res.content)
return True
def mkDir(dirName):
dirpath = os.path.join(sys.path[0], dirName)
if not os.path.exists(dirpath):
os.mkdir(dirpath)
return dirpath
def Tl_baidu_DownPic02(keyword, download_dir, pic_number):
word = keyword
dir2 = os.path.join(download_dir, word, get_sysdate())
print(dir2)
if not os.path.exists(dir2):
os.makedirs(dir2)
# dirpath = mkDir("results")
dirpath = dir2
urls = buildUrls(word)
index = 0
for url in urls:
# print("正在請求:", url)
html = requests.get(url, timeout=10).content.decode(
'utf-8') # 變量html 保留了一份Json文件,其中 objURL 是 圖片對應在網址
# print("正在請求:", html)
imgUrls = resolveImgUrl(html)
if len(imgUrls) == 0 or index >= pic_number: # 沒有圖片則結束
break
for url in imgUrls:
if downImg(url, dirpath, str(index) + ".jpg"):
index += 1
print("已下載 %s 張" % index)
if index >= pic_number:
break
if __name__ == '__main__':
# print("歡迎使用百度圖片下載腳本!\n目前僅支持單個關鍵詞。")
# print("下載結果保存在腳本目錄下的results文件夾中。")
# print("=" * 50)
# word = input("請輸入你要下載的圖片關鍵詞:\n")
Tl_baidu_DownPic02('Raspberry', 'e://', 50)
def call_DownPic02_main(keyword, download_dir, pic_number):
# print("歡迎使用百度圖片下載腳本!\n目前僅支持單個關鍵詞。")
# print("下載結果保存在腳本目錄下的results文件夾中。")
# print("=" * 50)
# word = input("請輸入你要下載的圖片關鍵詞:\n")
# Tl_baidu_DownPic02('Raspberry',50)
Tl_baidu_DownPic02(keyword, download_dir, pic_number)