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 | 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 |
-
+
-
+
-
-
+
+
+
-
-
-
+
+
-
-
-
+
+
+
| # fastest method, so default to google for now
if always_google:
google_ico2png(url)
if available(url) or only_google:
return
try: # look for /favicon.ico first
#print("favicon.ico")
log.FAVICON("try /favicon.ico")
direct_download("http://"+domain(url)+"/favicon.ico", file(url))
except:
try: # extract facicon filename from website <link rel>
#print("html <rel favicon>")
log.FAVICON("html <rel favicon>")
html_download(url)
except: # fallback
#print("google ico2png")
except Exception as e: # fallback
log.ERR(e)
google_ico2png(url)
# retrieve PNG via Google ico2png
def google_ico2png(url):
log.FAVICON("google ico2png")
#try:
GOOGLE = "http://www.google.com/s2/favicons?domain="
(fn, headers) = urllib.urlretrieve(GOOGLE+domain(url), file(url))
GOOGLE = "http://www.google.com/s2/favicons?domain="
(fn, headers) = urllib.urlretrieve(GOOGLE+domain(url), file(url))
# test for stub image
if delete_google_stub and (filesize(fn) in google_placeholder_filesizes):
os.remove(fn)
# test for stub image
if delete_google_stub and (filesize(fn) in google_placeholder_filesizes):
os.remove(fn)
def filesize(fn):
return os.stat(fn).st_size
|
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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401 | 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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290 |
-
+
-
+
-
+
-
-
-
+
-
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
-
-
-
+
+
-
-
-
-
+
+
+
+
| return "*/*"
# favicon.ico
def direct_download(favicon, fn):
# try:
# URL download
r = urllib.urlopen(favicon)
headers = r.info()
log.HTTP(headers)
# abort on
if r.getcode() >= 300:
raise Error("HTTP error" + r.getcode())
raise Exception("HTTP error %s" % r.getcode())
if not headers["Content-Type"].lower().find("image/") == 0:
raise Error("can't use text/* content")
raise Exception("can't use text/* content")
# save file
fn_tmp = fn+".tmp"
f = open(fn_tmp, "wb")
f.write(r.read(32768))
f.close()
# check type
if headers["Content-Type"].lower()=="image/png" and favicon.find(".png") and filetype(fn)=="image/png":
pngresize(fn_tmp)
os.mv(fn_tmp, fn)
else:
ico2png(fn_tmp, fn)
os.remove(fn_tmp)
# except:
# "File not found" and False
# peek at URL, download favicon.ico <link rel>
def html_download(url):
# <link rel>
#try:
# download html, look for @href in <link rel=shortcut icon>
r = urllib.urlopen(url)
html = r.read(4096)
r.close()
rx = re.compile("""<link[^<>]+rel\s*=\s*"?\s*(?:shortcut\s+|fav)?icon[^<>]+href=["'](?P<href>[^<>"']+)["'<>\s].""")
favicon = "".join(rx.findall(html))
log.DATA(favicon)
# url or
if favicon.startswith("http://"):
None
# just /pathname
else:
favicon = ahttp.urlparse.urljoin(url, favicon)
favicon = compat2and3.urlparse.urljoin(url, favicon)
log.FAVICON(favicon)
#favicon = "http://" + domain(url) + "/" + favicon
# download
direct_download(favicon, file(url))
#@obsolete since Pillow 2.1.x
#
# title: workaround for PIL.Image to preserve the transparency for .ico import
#
# http://stackoverflow.com/questions/987916/how-to-determine-the-transparent-color-index-of-ico-image-with-pil
# http://djangosnippets.org/snippets/1287/
#
# Author: dc
# Posted: January 17, 2009
# Languag: Python
# Django Version: 1.0
# Tags: pil image ico
# Score: 2 (after 2 ratings)
#
import operator
import struct
try:
from PIL import BmpImagePlugin, PngImagePlugin, Image
except Exception as e:
print("no PIL", e)
always_google = 1
only_google = 1
def load_icon(file, index=None):
'''
Load Windows ICO image.
See http://en.wikipedia.org/w/index.php?oldid=264332061 for file format
description.
'''
if isinstance(file, basestring):
file = open(file, 'rb')
try:
header = struct.unpack('<3H', file.read(6))
except:
raise IOError('Not an ICO file')
# Check magic
if header[:2] != (0, 1):
raise IOError('Not an ICO file')
# Collect icon directories
directories = []
for i in xrange(header[2]):
directory = list(struct.unpack('<4B2H2I', file.read(16)))
for j in xrange(3):
if not directory[j]:
directory[j] = 256
directories.append(directory)
if index is None:
# Select best icon
directory = max(directories, key=operator.itemgetter(slice(0, 3)))
else:
directory = directories[index]
# Seek to the bitmap data
file.seek(directory[7])
prefix = file.read(16)
file.seek(-16, 1)
if PngImagePlugin._accept(prefix):
# Windows Vista icon with PNG inside
image = PngImagePlugin.PngImageFile(file)
else:
# Load XOR bitmap
image = BmpImagePlugin.DibImageFile(file)
if image.mode == 'RGBA':
# Windows XP 32-bit color depth icon without AND bitmap
pass
else:
# Patch up the bitmap height
image.size = image.size[0], image.size[1] >> 1
d, e, o, a = image.tile[0]
image.tile[0] = d, (0, 0) + image.size, o, a
# Calculate AND bitmap dimensions. See
# http://en.wikipedia.org/w/index.php?oldid=264236948#Pixel_storage
# for description
offset = o + a[1] * image.size[1]
stride = ((image.size[0] + 31) >> 5) << 2
size = stride * image.size[1]
# Load AND bitmap
file.seek(offset)
string = file.read(size)
mask = Image.fromstring('1', image.size, string, 'raw',
('1;I', stride, -1))
image = image.convert('RGBA')
image.putalpha(mask)
return image
# convert .ico file to .png format
def ico2png(ico, png_fn):
#print("ico2png", ico, png, image)
try: # .ico
image = load_icon(ico, None)
except: # automatic img file type guessing
image = Image.open(ico)
# resize
if image.size[0] > 16:
image.resize((16, 16), Image.ANTIALIAS)
log.ICO2PNG(ico, png, image)
# resize
if image.size[0] > 16:
image.resize((16, 16), Image.ANTIALIAS)
# .png format
image.save(png_fn, "PNG", quality=98)
# .png format
image.save(png_fn, "PNG", quality=98)
# resize an image
def pngresize(fn, x=16, y=16):
image = Image.open(fn)
if image.size[0] > x:
image.resize((x, y), Image.ANTIALIAS)
image.save(fn, "PNG", quality=98)
image = Image.open(fn)
if image.size[0] > x:
image.resize((x, y), Image.ANTIALIAS)
image.save(fn, "PNG", quality=98)
#-- test
if __name__ == "__main__":
import sys
download(sys.argv[1])
|