我們來(lái)寫(xiě)一個(gè)簡(jiǎn)單的百度圖片下載器,過(guò)程如下:
1.百度圖片爬蟲(chóng)
2.eric6 和 qt designer 設(shè)計(jì) GUI界面
3.將桌面程序和爬蟲(chóng)程序整合在一起
4.打包程序
一、百度圖片下載爬蟲(chóng)
這個(gè)在爬蟲(chóng)文集里有,實(shí)現(xiàn)原理請(qǐng)戳這 爬百度圖片
由于咱們是要整合到 GUI 程序里,所以這里將它寫(xiě)為一個(gè)類(lèi):
import requests
import urllib
import os, re
import itertools
class Spider(object):
def __init__(self, keyword):
self.keyword = keyword
self.urls = self.buildUrls()
self.sign_table = {
'_z2C$q': ':',
'_z&e3B': '.',
'AzdH3F': '/'
}
self.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'
}
self.char_table = {ord(key): ord(value) for key, value in self.char_table.items()}
def decode(self, url):
for key, value in self.sign_table.items():
url = url.replace(key, value)
return url.translate(self.char_table)
def buildUrls(self):
word = urllib.parse.quote(self.keyword)
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))
return urls
def resolveImgUrl(self, html):
re_url = re.compile(r'"objURL":"(.*?)"')
imgUrls = [self.decode(x) for x in re_url.findall(html)]
return imgUrls
def downImg(self, 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 get_path(self):
dirpath = os.getcwd() + '\\pictures'
if not os.path.isdir(dirpath):
os.mkdir(dirpath)
return dirpath
def Download(self):
dirpath = self.get_path()
index = 0
for url in self.urls:
html = requests.get(url, timeout=10).content.decode('utf-8')
imgUrls = self.resolveImgUrl(html)
if len(imgUrls) == 0:
break
for url in imgUrls:
if self.downImg(url, dirpath, str(index) + ".jpg"):
index += 1
print("已下載 %s 張" % index)
return index
if __name__ == "__main__":
a = Spider("美女")
a.Download()
運(yùn)行該文件將把圖片下載該目錄下的 picture 文件夾內(nèi)。
命名為 BaiduSpider.py,先保存下來(lái)。
二、接著來(lái)設(shè)計(jì) GUI 界面
打開(kāi) eric6,新建下項(xiàng)目,具體過(guò)程見(jiàn)教程(一)里面的鏈接文章
點(diǎn)擊窗體,在空白處右鍵新建個(gè)窗體,就命名為 window吧
可以看到窗口里生成了 window.ui 文件
并且自動(dòng)跳入 qt designer
先實(shí)現(xiàn)最基本的界面,添加倆個(gè) label,文字改為“請(qǐng)輸入關(guān)鍵詞” 和“————”, 在右上角添加一個(gè)lineEdit, 還有倆個(gè) pushbutton 文字改為“開(kāi)始下載” 和 “退出”。
給退出按鈕加上信號(hào)槽。
點(diǎn)擊 ok ,可以看到退出的動(dòng)作信號(hào)已經(jīng)好了
保存下文件(工具欄第三個(gè)按鈕),關(guān)閉qt designer 回到 eric6
右鍵我們剛保存的 window.ui 文件,選擇編譯窗口,提示編譯成功,回到源代碼欄,多出了個(gè)UI_windows.py文件
右鍵該文件,打開(kāi),在開(kāi)始中選運(yùn)行腳本,發(fā)現(xiàn)我們剛設(shè)計(jì)的 GUI 窗口出現(xiàn)了,點(diǎn)擊退出,窗口關(guān)閉
那么我們一個(gè)簡(jiǎn)單的 GUI 設(shè)計(jì)到此算完成了
三、整合
關(guān)閉 eric6, 復(fù)制下UI_windows.py文件,改名為 main.py,以及把第一步的 BaiduSpider.py 也放在這個(gè)文件夾
接著編輯 main.py,先打開(kāi)
# -*- coding: utf-8 -*-
# Form implementation generated from reading ui file 'E:\Python項(xiàng)目\Pyqt\eric\百度圖片下載器\window.ui'
#
# Created by: PyQt5 UI code generator 5.6
#
# WARNING! All changes made in this file will be lost!
from PyQt5 import QtCore, QtGui, QtWidgets
class Ui_Dialog(object):
def setupUi(self, Dialog):
Dialog.setObjectName("Dialog")
Dialog.resize(527, 351)
Dialog.setSizeGripEnabled(True)
self.label = QtWidgets.QLabel(Dialog)
self.label.setGeometry(QtCore.QRect(70, 70, 101, 16))
self.label.setObjectName("label")
self.lineEdit = QtWidgets.QLineEdit(Dialog)
self.lineEdit.setGeometry(QtCore.QRect(232, 70, 141, 21))
self.lineEdit.setObjectName("lineEdit")
self.label_2 = QtWidgets.QLabel(Dialog)
self.label_2.setGeometry(QtCore.QRect(60, 170, 161, 31))
self.label_2.setObjectName("label_2")
self.pushButton = QtWidgets.QPushButton(Dialog)
self.pushButton.setGeometry(QtCore.QRect(270, 180, 93, 28))
self.pushButton.setObjectName("pushButton")
self.pushButton_2 = QtWidgets.QPushButton(Dialog)
self.pushButton_2.setGeometry(QtCore.QRect(350, 290, 93, 28))
self.pushButton_2.setObjectName("pushButton_2")
self.retranslateUi(Dialog)
self.pushButton_2.clicked.connect(Dialog.close)
QtCore.QMetaObject.connectSlotsByName(Dialog)
def retranslateUi(self, Dialog):
_translate = QtCore.QCoreApplication.translate
Dialog.setWindowTitle(_translate("Dialog", "百度圖片下載器"))
self.label.setText(_translate("Dialog", "請(qǐng)輸入關(guān)鍵詞:"))
self.label_2.setText(_translate("Dialog", "________________"))
self.pushButton.setText(_translate("Dialog", "開(kāi)始下載"))
self.pushButton_2.setText(_translate("Dialog", "退出"))
if __name__ == "__main__":
import sys
app = QtWidgets.QApplication(sys.argv)
Dialog = QtWidgets.QDialog()
ui = Ui_Dialog()
ui.setupUi(Dialog)
Dialog.show()
sys.exit(app.exec_())
先把開(kāi)頭的注釋刪掉,然后分析下代碼
setupUI 這個(gè)方法主要是建立我們的 GUI 布局,retranslateUi 方法則設(shè)置了一些文本內(nèi)容,(由于在設(shè)計(jì) GUI 的時(shí)候我并沒(méi)有對(duì)每個(gè)元素進(jìn)行相應(yīng)的命名,剛好可以從這看出元素的名字)
先設(shè)置 lineEdit, 在用戶輸入什么內(nèi)容時(shí),將內(nèi)容發(fā)送到label_2。
self.lineEdit.textChanged[str].connect(self.onChanged)
在 setupUI方法里關(guān)于 lineEdit 添加上面代碼,并新增 onChanged 方法。
def onChanged(self, text):
self.label_2.setText(text)
self.label_2.adjustSize()
self.keyword = text
如果 lineEdit的內(nèi)容發(fā)生了改變,即用戶輸入了內(nèi)容,就會(huì)將內(nèi)容發(fā)送到 label_2 并調(diào)整大小。然后創(chuàng)建私有變量 self.keyword(后面百度圖片下載要傳入的關(guān)鍵詞)
在用戶輸入內(nèi)容后,點(diǎn)擊開(kāi)始下載則下載圖片,所以在 setupUI 里加上
self.pushButton.clicked.connect(self.Download)
添加 Download方法
def Download(self.setText("正在下載")
a = BaiduSpider.Spider(self.keyword)
a.Download()
當(dāng)點(diǎn)擊開(kāi)始下載后,則將按鈕文字改為“正在下載”,創(chuàng)建 BaiduSpider 實(shí)例,傳入關(guān)鍵詞,然后開(kāi)始下載圖片。記得在帶面前面 導(dǎo)入BaiduSpider。即
import BaiduSpider
改完代碼如下:
from PyQt5 import QtCore, QtGui, QtWidgets
import BaiduSpider
class Ui_Dialog(object):
def setupUi(self, Dialog):
Dialog.setObjectName("Dialog")
Dialog.resize(527, 351)
Dialog.setSizeGripEnabled(True)
self.label = QtWidgets.QLabel(Dialog)
self.label.setGeometry(QtCore.QRect(70, 70, 101, 16))
self.label.setObjectName("label")
self.lineEdit = QtWidgets.QLineEdit(Dialog)
self.lineEdit.setGeometry(QtCore.QRect(232, 70, 141, 21))
self.lineEdit.setObjectName("lineEdit")
self.lineEdit.textChanged[str].connect(self.onChanged)
self.label_2 = QtWidgets.QLabel(Dialog)
self.label_2.setGeometry(QtCore.QRect(60, 170, 161, 31))
self.label_2.setObjectName("label_2")
self.pushButton = QtWidgets.QPushButton(Dialog)
self.pushButton.setGeometry(QtCore.QRect(270, 180, 93, 28))
self.pushButton.setObjectName("pushButton")
self.pushButton_2 = QtWidgets.QPushButton(Dialog)
self.pushButton_2.setGeometry(QtCore.QRect(350, 290, 93, 28))
self.pushButton_2.setObjectName("pushButton_2")
self.retranslateUi(Dialog)
self.pushButton_2.clicked.connect(Dialog.close)
QtCore.QMetaObject.connectSlotsByName(Dialog)
self.pushButton.clicked.connect(self.Download)
def retranslateUi(self, Dialog):
_translate = QtCore.QCoreApplication.translate
Dialog.setWindowTitle(_translate("Dialog", "百度圖片下載器"))
self.label.setText(_translate("Dialog", "請(qǐng)輸入關(guān)鍵詞:"))
self.label_2.setText(_translate("Dialog", "________________"))
self.pushButton.setText(_translate("Dialog", "開(kāi)始下載"))
self.pushButton_2.setText(_translate("Dialog", "退出"))
def onChanged(self, text):
self.label_2.setText(text)
self.label_2.adjustSize()
self.keyword = text
def Download(self):
self.pushButton.setText("正在下載")
a = BaiduSpider.Spider(self.keyword)
a.Download()
if __name__ == "__main__":
import sys
app = QtWidgets.QApplication(sys.argv)
Dialog = QtWidgets.QDialog()
ui = Ui_Dialog()
ui.setupUi(Dialog)
Dialog.show()
sys.exit(app.exec_())
運(yùn)行看看
發(fā)現(xiàn)有個(gè)意外,就是下載時(shí)程序就不能被選中了,再點(diǎn)擊就會(huì)卡死。應(yīng)該是線程中通信的問(wèn)題,這個(gè)先忽略下。
四、解決阻塞
在上面的程序中,當(dāng)我們開(kāi)始下載圖片時(shí),由于該下載任務(wù)時(shí)長(zhǎng)較久,就會(huì)阻塞程序,詳情見(jiàn)這篇文章[http://www.lxweimin.com/p/ed47a8959854]
(pyqt多進(jìn)程防阻塞)
按照這樣我們來(lái)修改下代碼
先導(dǎo)入 QTthread
from PyQt5.QtCore import *
再修改下面這些
from PyQt5 import QtCore, QtGui, QtWidgets
import BaiduSpider
from PyQt5.QtCore import *
class Ui_Dialog(object):
def setupUi(self, Dialog):
Dialog.setObjectName("Dialog")
Dialog.resize(527, 351)
Dialog.setSizeGripEnabled(True)
self.label = QtWidgets.QLabel(Dialog)
self.label.setGeometry(QtCore.QRect(70, 70, 101, 16))
self.label.setObjectName("label")
self.lineEdit = QtWidgets.QLineEdit(Dialog)
self.lineEdit.setGeometry(QtCore.QRect(232, 70, 141, 21))
self.lineEdit.setObjectName("lineEdit")
self.lineEdit.textChanged[str].connect(self.onChanged)
self.label_2 = QtWidgets.QLabel(Dialog)
self.label_2.setGeometry(QtCore.QRect(60, 170, 161, 31))
self.label_2.setObjectName("label_2")
self.pushButton = QtWidgets.QPushButton(Dialog)
self.pushButton.setGeometry(QtCore.QRect(270, 180, 93, 28))
self.pushButton.setObjectName("pushButton")
self.pushButton_2 = QtWidgets.QPushButton(Dialog)
self.pushButton_2.setGeometry(QtCore.QRect(350, 290, 93, 28))
self.pushButton_2.setObjectName("pushButton_2")
self.retranslateUi(Dialog)
self.pushButton_2.clicked.connect(Dialog.close)
QtCore.QMetaObject.connectSlotsByName(Dialog)
self.pushButton.clicked.connect(self.Download)
def retranslateUi(self, Dialog):
_translate = QtCore.QCoreApplication.translate
Dialog.setWindowTitle(_translate("Dialog", "百度圖片下載器"))
self.label.setText(_translate("Dialog", "請(qǐng)輸入關(guān)鍵詞:"))
self.label_2.setText(_translate("Dialog", "________________"))
self.pushButton.setText(_translate("Dialog", "開(kāi)始下載"))
self.pushButton_2.setText(_translate("Dialog", "退出"))
def onChanged(self, text):
self.label_2.setText(text)
self.label_2.adjustSize()
self.keyword = text
def Download(self):
self.pushButton.setText("正在下載")
self.thread = RunThread(self.keyword)
self.thread.start()
class RunThread(QThread):
trigger = pyqtSignal()
def __init__(self,keyword):
super(RunThread, self).__init__()
self.key = keyword
def run(self):
a = BaiduSpider.Spider(self.key)
a.Download()
self.trigger.emit()
if __name__ == "__main__":
import sys
app = QtWidgets.QApplication(sys.argv)
Dialog = QtWidgets.QDialog()
ui = Ui_Dialog()
ui.setupUi(Dialog)
Dialog.show()
sys.exit(app.exec_())
運(yùn)行下,發(fā)現(xiàn)問(wèn)題已經(jīng)解決,但圖片下載速度好像有點(diǎn)慢
這時(shí)我們可以把百度圖片爬蟲(chóng)換成多線程的,在上文的文章里有多線程版本,這里就不重復(fù)了,同樣改成一個(gè)類(lèi)就行。
五、打包程序
用 pyinstaller 就行了,用pip下載完
在該目錄下按住 shift 右鍵打開(kāi)選擇在此打開(kāi)命令行,輸入
pyinstaller -F main.py
過(guò)一會(huì)兒文件就打包完成了,在 dist 目錄下可以發(fā)現(xiàn)有個(gè) main.exe文件,挺大的。這個(gè)文件可以單獨(dú)運(yùn)行了,打開(kāi),等一會(huì)兒就會(huì)跳出我們的 GUI界面,然后就可以下載圖片了。
雖然挺簡(jiǎn)陋的,但起碼也是不錯(cuò)的哈