I'm using QNetworkAccessManager for downloading images.
At the first time, I must specify the url of images.
But it is different by means.
For example, I get from an image from Wikipedia Top Page Japanese.
There are some uploading images.
If I copy the texts and images , and then paste them into my editor, the html text contains the url.
Even if I pass it into the QNetworkRequest, I cannot download the image.
After I dig into the url and arrive at the image file in Wikipedia Commons,
If I pass the url into the QNetworkRequest,I can download images.
I have already understood the url must be exact,but I don't know how to differenciate them.
Do you know how to download programmatically the images every time without mistaking?
Is there any way to know the exact url in advance?
I have no much knowledge about network.
I often accept UnknownContentError
How to use for sample code
Ctrl+C copy texts & images (please contain image.) Ctrl+V paste html & download image
Qdownload image directly. I can download by this only.
Sample Code
from PySide import QtCore, QtGui, QtNetwork
from bs4 import BeautifulSoup
import sys, os, re
class Widget(QtGui.QTextEdit):
def __init__(self, parent=None):
super(Widget, self).__init__()
def keyPressEvent(self, event):
if event.modifiers() == QtCore.Qt.KeyboardModifier.ControlModifier and event.key() == QtCore.Qt.Key_C:
tc = self.textCursor()
mimedata = self.createMimeDataFromSelection()
clipboard = QtGui.QApplication.clipboard()
clipboard.setMimeData(mimedata)
start = tc.selectionStart()
end = tc.selectionEnd()
char = tc.charFormat()
char.clearBackground()
tc.setCharFormat(char)
return
elif event.modifiers() == QtCore.Qt.KeyboardModifier.ControlModifier and event.key() == QtCore.Qt.Key_V:
clipboard = QtGui.QApplication.clipboard()
html = clipboard.mimeData().html()
pous = BeautifulSoup(html,"lxml")
image_items = pous.find_all('a', href=re.compile('(\.jpg|\.png|\.svg|\.gif)$'))
image_urls = [item.get('href') for item in image_items]
for i, url in enumerate(image_urls):
#indirect url https://ja.wikipedia.org/wiki/%E3%83%95%E3%82%A1%E3%82%A4%E3%83%AB:Oguri_Cap_in_Yushun_Stallion_station.jpg
print(url)
request = QtNetwork.QNetworkRequest(QtCore.QUrl(url))
self.nam = QtNetwork.QNetworkAccessManager()
self.nam.finished[QtNetwork.QNetworkReply].connect(self.doReply)
self.nam.get(request)
if event.key() == QtCore.Qt.Key_Q:
self.doRequest()
def doRequest(self):
# direct url & exact url
url = "https://upload.wikimedia.org/wikipedia/commons/c/c3/Oguri_Cap_in_Yushun_Stallion_station.jpg"
req = QtNetwork.QNetworkRequest(QtCore.QUrl(url))
self.nam = QtNetwork.QNetworkAccessManager()
self.nam.finished[QtNetwork.QNetworkReply].connect(self.doReply)
self.nam.get(req)
def doReply(self, reply):
er = reply.error()
if er == QtNetwork.QNetworkReply.NoError:
data = reply.readAll()
self.saveImage(data)
else:
print( "Error occured: ", er)
print( reply.errorString())
def saveImage(self, data):
try:
im = QtGui.QImageWriter()
im.setFileName(os.path.join(os.getcwd(),"wiki_topimage.png"))
imd = QtGui.QImage()
imd_bool = imd.loadFromData(data.data())
im.write(imd)
except Exception as e:
print(e)
def main():
QtCore.QCoreApplication.addLibraryPath(os.path.join(os.getcwd(),"plugins"))
try:
QtGui.QApplication([])
except Exception as e:
print("error", e)
w = Widget()
w.show()
sys.exit(QtGui.QApplication.exec_())
if __name__ == "__main__":
main()
You have the following errors:
https://ja.wikipedia.org/wiki/%E3%83%95%E3%82%A1%E3%82%A4%E3%83%AB:Oguri_Cap_in_Yushun_Stallion_station.jpg
to
https://ja.wikipedia.org/wiki/ファイル:Oguri_Cap_in_Yushun_Stallion_station.jpg
import os
import sys
import re
from PySide import QtCore, QtGui, QtNetwork
from bs4 import BeautifulSoup
class Widget(QtGui.QTextEdit):
def __init__(self, parent=None):
super(Widget, self).__init__(parent)
self.nam = QtNetwork.QNetworkAccessManager(self)
self.nam.finished[QtNetwork.QNetworkReply].connect(self.doReply)
def keyPressEvent(self, event):
if event.matches(QtGui.QKeySequence.Copy):
tc = self.textCursor()
mimedata = self.createMimeDataFromSelection()
clipboard = QtGui.QApplication.clipboard()
clipboard.setMimeData(mimedata)
start = tc.selectionStart()
end = tc.selectionEnd()
char = tc.charFormat()
char.clearBackground()
tc.setCharFormat(char)
return
elif event.matches(QtGui.QKeySequence.Paste):
clipboard = QtGui.QApplication.clipboard()
html = clipboard.mimeData().html()
pous = BeautifulSoup(html, "lxml")
image_items = pous.find_all(
"a", href=re.compile(r"(\.jpg|\.png|\.svg|\.gif)$")
)
for i, item in enumerate(image_items):
url = item.find("img", recursive=False).get("src")
print(i, url)
request = QtNetwork.QNetworkRequest(
QtCore.QUrl.fromUserInput(url)
)
self.nam.get(request)
@QtCore.Slot(QtNetwork.QNetworkReply)
def doReply(self, reply):
er = reply.error()
if er == QtNetwork.QNetworkReply.NoError:
print("ok", reply.url())
name = reply.url().path().split("/")[-1]
filename = os.path.join(os.getcwd(), name)
file = QtCore.QFile(filename)
if file.open(QtCore.QIODevice.WriteOnly):
file.write(reply.readAll())
else:
print("Error occured: ", er, reply.url())
reply.deleteLater()
def main():
QtCore.QCoreApplication.addLibraryPath(os.path.join(os.getcwd(), "plugins"))
app = QtGui.QApplication.instance()
if app is None:
app = QtGui.QApplication(sys.argv)
w = Widget()
w.show()
sys.exit(QtGui.QApplication.exec_())
if __name__ == "__main__":
main()