- How to create a custom data type that can be read off wx.Clipboard
- Getting CF_HTML off the clipboard in a cross-platform manner
- How to create a custom data type that can be read off wx.Clipboard
- Getting CF_HTML off the clipboard in a cross-platform manner
- Script for the clipboard -> blog transfer
- Notelets
- Today's pictures
- Yesterday's pictures
- Open Threads
How to create a custom data type that can be read off wx.Clipboard
/ClipboardAndCustomDataInWxPython
Getting CF_HTML off the clipboard in a cross-platform manner
I have written Win32-oriented Python code to copy 'HTML Format' data from the Win32 clipboard into a new message on my blog. Now, I'm trying to translate this code so that it can work on OS X and Linux. The obvious place to start for me is using wxPython, specifically ![[WWW]](/www/moin/htdocs/classic/img/moin-www.png){kind=small}
wx.Clipboard, wx.DataObject, specifically wx.DataObjectSimple.
I've been trying to figure out to read custom items off wx.Clipboard. I am able to read off different formats using Win32 specific methods.
Consider the example of copying a selection from a HTML page in Firefox 1.0.7 on Windows XP. I can see the available data formats on the clipboard by running getAvailableFormats() (see code below):
>>> ClipboardToBlog.getAvailableFormats()
{'CF_TEXT': 1, 'CF_LOCALE': 16, 'text/_moz_htmlcontext': 49898, 'text/html': 49308, 'text/_moz_htmlinfo': 49935, 'Ole Private Data': 49171, 'DataObject': 49161, 'CF_OEMTEXT': 7, 'HTML Format': 49426, 'CF_UNICODETEXT': 13}
I can read off the text format from the clipboard with
How to create a custom data type that can be read off wx.Clipboard
I've been trying to create a custom wx.DataObject that I can put and get off the wx.Clipboard.
Getting CF_HTML off the clipboard in a cross-platform manner
I have written Win32-oriented Python code to copy 'HTML Format' data from the Win32 clipboard into a new message on my blog. Now, I'm trying to translate this code so that it can work on OS X and Linux. The obvious place to start for me is using wxPython, specifically wx.Clipboard, wx.DataObject, specifically wx.DataObjectSimple.
I've been trying to figure out to read custom items off wx.Clipboard. I am able to read off different formats using Win32 specific methods.
Consider the example of copying a selection from a HTML page in Firefox 1.0.7 on Windows XP. I can see the available data formats on the clipboard by running getAvailableFormats() (see code below):
>>> ClipboardToBlog.getAvailableFormats()
{'CF_TEXT': 1, 'CF_LOCALE': 16, 'text/_moz_htmlcontext': 49898, 'text/html': 49308, 'text/_moz_htmlinfo': 49935, 'Ole Private Data': 49171, 'DataObject': 49161, 'CF_OEMTEXT': 7, 'HTML Format': 49426, 'CF_UNICODETEXT': 13}
I can read off the text format from the clipboard with
1 2 3 4 5 6 7 8 9 10 11 12 13 14 | def GetTextFromClipboard():
"""
"""
clipboard = wx.Clipboard()
if clipboard.Open():
if clipboard.IsSupported(wx.DataFormat(wx.DF_TEXT)):
data = wx.TextDataObject()
clipboard.GetData(data)
s = data.GetText()
clipboard.Close()
clipboard.Close()
return s
else:
return None |
e.g.,
>>> LearningWxClipboard.GetTextFromClipboard() u"I have written Win32-oriented Python code to copy 'HTML Format' data from the Win32 clipboard into a new message on my blog. Now, I'm trying to translate this code so that it can work on OS X and Linux. The obvious place to start for me is using wxPython, specifically [WWW]wx.Clipboard, [WWW]wx.DataObject, specifically [WWW]wx.DataObjectSimple.\r\n\r\n"
Now, I want to retrieve the 'HTML Format' data. First, I set up the wx.DataFormat
1 2 3 | #! python
CFHtmlFormat = wx.DataFormat(0)
CFHtmlFormat.SetId('HTML Format') |
Note that
1 | CFHtmlFormat.GetType() |
[writing in progress....]
Script for the clipboard -> blog transfer
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 |
#AUTHOR: Raymond Yee. You are free to use/reuse this code with attribution.
#module ClipboardToBlog
__all__ = ['cb2RY','cb2IU']
import win32clipboard
from BaseHTMLProcessor import BaseHTMLProcessor
class CommentStripper (BaseHTMLProcessor):
"""
strip comments
"""
def __init__(self):
BaseHTMLProcessor.__init__(self)
def handle_comment(self, text):
pass
class MoinIconStripper(BaseHTMLProcessor):
"""
if it's a moin-www.png and the alt is [WWW], strip it away
"""
def __init__(self,s):
BaseHTMLProcessor.__init__(self)
self.feed(s)
self.close()
def start_img(self, attrs):
import os.path
attrhash = {}
for (key, value) in attrs:
attrhash[key] = value
try:
src = attrhash['src']
imgfile = os.path.split(src)[1]
alt = attrhash['alt']
if not ((imgfile == 'moin-www.png') and (alt == '[WWW]')):
BaseHTMLProcessor.unknown_starttag(self, 'img', attrs)
except:
BaseHTMLProcessor.unknown_starttag(self, 'img', attrs)
def __str__(self):
return self.output()
class CF_HTML_Exception(Exception):
pass
class CF_HTML:
"""
s is of the form CF_HTML
"""
def __init__(self,s):
self.parseOut(s)
def parseOut(self,s):
from string import split
import re
# pick out version, start, end
rawstr = r"""^Version:(.+)$"""
match_obj = re.search(rawstr, s, re.MULTILINE)
if (match_obj):
version = match_obj.group(1)
else:
raise CF_HTML_Exception('Cannot find version in CF_HTML')
rawstr = r"""^StartHTML:(.+)$"""
match_obj = re.search(rawstr, s, re.MULTILINE)
if (match_obj):
StartHTML = int(match_obj.group(1))
else:
raise CF_HTML_Exception('Cannot find StartHTML in CF_HTML')
rawstr = r"""^EndHTML:(.+)$"""
match_obj = re.search(rawstr, s, re.MULTILINE)
if (match_obj):
EndHTML = int(match_obj.group(1))
else:
raise CF_HTML_Exception('Cannot find EndHTML in CF_HTML')
rawstr = r"""^StartFragment:(.+)$"""
match_obj = re.search(rawstr, s, re.MULTILINE)
if (match_obj):
StartFragment = int(match_obj.group(1))
else:
raise CF_HTML_Exception('Cannot find StartFragment in CF_HTML')
rawstr = r"""^EndFragment:(.+)$"""
match_obj = re.search(rawstr, s, re.MULTILINE)
if (match_obj):
EndFragment = int(match_obj.group(1))
else:
raise CF_HTML_Exception('Cannot find EndFragment in CF_HTML')
#print version,StartHTML, EndHTML, StartFragment, EndFragment
self.htmlString = s[StartHTML:EndHTML]
htmlFragment = s[StartFragment:EndFragment]
# strip comments from htmlFragment
#print htmlString
parser = CommentStripper()
parser.feed(htmlFragment)
parser.close()
self.htmlFragment = parser.output()
def getCF_HTML():
af = getAvailableFormats()
if af.has_key('HTML Format'):
win32clipboard.OpenClipboard()
s = win32clipboard.GetClipboardData (af['HTML Format'])
win32clipboard.CloseClipboard()
return s
else:
return None
def buildNativeFormatList():
"""
builds a dictionary mapping
"""
import win32clipboard
h = {}
keys = win32clipboard.__dict__.keys()
for key in keys:
if key[0:3] == 'CF_':
val = int(eval('win32clipboard.' + key))
h[val] = key
return h
def getAvailableFormats():
availableFormats = {}
win32clipboard.OpenClipboard()
#print "There are %s formats available" % (str(win32clipboard.CountClipboardFormats()))
val = win32clipboard.EnumClipboardFormats(0)
nativeFormats = buildNativeFormatList()
#print 'nativeFormats', nativeFormats
while(val):
try:
format = win32clipboard.GetClipboardFormatName(val)
#print val, format
availableFormats[format]=val
except:
if nativeFormats.has_key(val):
format = nativeFormats[val]
availableFormats[format]=val
else:
if availableFormats.has_key('UNKNOWN'):
availableFormats['UNKNOWN'] = availableFormats['UNKNOWN'].append(val)
else:
availableFormats['UNKNOWN'] = [val]
val = win32clipboard.EnumClipboardFormats(val)
win32clipboard.CloseClipboard()
return availableFormats
class MTAccount:
def __init__(self,user,password,url,blogediturl,blogID):
self.user = user
self.password = password
self.url = url
self.blogediturl = blogediturl
self.blogID = blogID
def postToMT(account,body):
from PyMT import PyMT
import webbrowser
mt = PyMT(account.url,account.user,account.password)
content = {'title':'New Post', 'description':body, 'categories':[0] }
try:
postID = mt.newPost(account.blogID,content,0)
webbrowser.open(account.blogediturl % (str(postID),str(account.blogID)))
except:
print 'error in posting to MT'
class ManilaAccount:
def __init__(self,user,password,url):
self.user = user
self.password = password
self.url = url
def postNewsItemToManila(account,body):
from manilalib import Site, NewsItem
s = Site(account.url,account.user,account.password)
newsitem = NewsItem('New Post','htt://raymondyee.net/wiki',body,'Unclassified')
try:
s.messages.append(newsitem)
return len(s.messages)
except:
'error in posting to Manila'
def cb2RY():
s = getCF_HTML()
if s:
cfhtml = CF_HTML(s)
mtaccount = MTAccount('USER','PASSWORD','http://raymondyee.net/mt/mt-xmlrpc.cgi',"http://raymondyee.net/mt/mt.cgi?__mode=view&_type=entry&id=%s&blog_id=%s",'1')
postToMT(mtaccount, str(MoinIconStripper(cfhtml.htmlFragment)))
def cb2IU():
s = getCF_HTML()
if s:
cfhtml = CF_HTML(s)
account = ManilaAccount('USER','PASSWORD','http://iu.berkeley.edu/rdhyee')
postNewsItemToManila(account,str(MoinIconStripper(cfhtml.htmlFragment)))
if __name__ == '__main__':
import sys
if len(sys.argv):
dir = sys.argv[1]
if (dir == 'RY'):
cb2RY()
if (dir == 'IU'):
cb2IU() |
Notelets
Personal
Laura and I celebrate 6 months of wedded blissful happiness today!
Work
Today's pictures
|
|
|
Yesterday's pictures
|
Open Threads
I usually like to work in parallel on a number of entries. Here I list them so they can be easily noted and accessed:
-
....
