FreeCAD /src/Tools/offlinedoc/downloadwiki.py

Language Python Lines 295
MD5 Hash 349e82f0bef63a112e7291c2c170ab18
Repository https://github.com/emagdalena/FreeCAD.git View Raw File
  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
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
#!/usr/bin/env python

#***************************************************************************
#*                                                                         *
#*   Copyright (c) 2009 Yorik van Havre <yorik@uncreated.net>              *  
#*                                                                         *
#*   This program is free software; you can redistribute it and/or modify  *
#*   it under the terms of the GNU Lesser General Public License (LGPL)    *
#*   as published by the Free Software Foundation; either version 2 of     *
#*   the License, or (at your option) any later version.                   *
#*   for detail see the LICENCE text file.                                 *
#*                                                                         *
#*   This program is distributed in the hope that it will be useful,       *
#*   but WITHOUT ANY WARRANTY; without even the implied warranty of        *
#*   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the         *
#*   GNU Library General Public License for more details.                  *
#*                                                                         *
#*   You should have received a copy of the GNU Library General Public     *
#*   License along with this program; if not, write to the Free Software   *
#*   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  *
#*   USA                                                                   *
#*                                                                         *
#***************************************************************************

__title__="downloadwiki"
__author__ = "Yorik van Havre <yorik@uncreated.net>"
__url__ = "http://free-cad.sf.net"

"""
This script retrieves the contents of a wiki site from a pages list
"""

import sys, os, re, tempfile, getopt
from urllib2 import urlopen, HTTPError

#    CONFIGURATION       #################################################

DEFAULTURL = "http://sourceforge.net/apps/mediawiki/free-cad" #default URL if no URL is passed
INDEX = "Online_Help_Toc" # the start page from where to crawl the wiki
NORETRIEVE = ['Manual','Developer_hub','Power_users_hub','Users_hub','Source_documentation', 'User_hub','Main_Page','About_this_site'] # pages that won't be fetched (kept online)
GETTRANSLATIONS = False # Set true if you want to get the translations too.
MAXFAIL = 3 # max number of retries if download fails
VERBOSE = True # to display what's going on. Otherwise, runs totally silent.

#    END CONFIGURATION      ##############################################

FOLDER = "./localwiki"
LISTFILE = "wikifiles.txt"
URL = DEFAULTURL
wikiindex = "/index.php?title="
defaultfile = "<html><head><link type='text/css' href='wiki.css' rel='stylesheet'></head><body>&nbsp;</body></html>"
css = """
/* Basic CSS for offline wiki rendering */

body {
  font-family: Arial,Helvetica,sans-serif;
  font-size: 13px;
  text-align: justify;
  background: #ffffff;
  color: #000000;
  }

h1 {
  font-size: 2.2em;
  font-weight: bold;
  background: #46A4D0;
  color: white;
  padding: 5px;
  border-radius: 5px;
  }

pre {
  border: 1px solid #888888;
  text-align: left;
  background: #EEEEEE;
  padding: 5px;
  border-radius: 5px;
  }

a:link, a:visited {
  font-weight: bold;
  text-decoration: none;
  color: #0084FF;
  }

a:hover {
  text-decoration: underline;
  }

.printfooter {
  font-size: 0.8em;
  color: #333333;
  border-top: 1px solid #333333;
  }

.wikitable #toc {
  font-size: 0.8em;
  }

#toc,.docnav {
  display: none;
  }

.ct, .ctTitle, .ctOdd, .ctEven th {
  text-align: left;
  width: 200px;
  float: right;
  background: #eeeeee;
  }
"""

def crawl():
    "downloads an entire wiki site"
    processed = []
    if VERBOSE: print "crawling ", URL, ", saving in ", FOLDER
    if not os.path.isdir(FOLDER): os.mkdir(FOLDER)
    file = open(FOLDER + os.sep + "wiki.css",'wb')
    file.write(css)
    file.close()
    dfile = open(FOLDER + os.sep + "default.html",'wb')
    dfile.write(defaultfile)
    dfile.close()
    lfile = open(LISTFILE)
    global locallist
    locallist = []
    for l in lfile: locallist.append(l.replace("\n",""))
    lfile.close()
    todolist = locallist[:]
    print "getting",len(todolist),"files..."
    count = 1
    indexpages = get(INDEX)
    while todolist:
        targetpage = todolist.pop()
        if VERBOSE: print count, ": Fetching ", targetpage
        get(targetpage)
        count += 1
    if VERBOSE: print "Fetched ", count, " pages"
    if VERBOSE: print "All done!"
    return 0

def get(page):
    "downloads a single page, returns the other pages it links to"
    if page[-4:] in [".png",".jpg",".svg",".gif","jpeg"]:
        print "getting image",page
        fetchimage(page)
    elif not exists(page):
        html = fetchpage(page)
        html = cleanhtml(html)
        pages = getlinks(html)
        html = cleanlinks(html,pages)
        html = cleanimagelinks(html)
        output(html,page)
    else:
        if VERBOSE: print "skipping",page

def getlinks(html):
    "returns a list of wikipage links in html file"
    links = re.findall('<a[^>]*>.*?</a>',html)
    pages = []
    for l in links:
        # rg = re.findall('php\?title=(.*)\" title',l)
        rg = re.findall('href=.*?php\?title=(.*?)"',l)
        if rg:
            rg = rg[0]
            if "#" in rg:
                rg = rg.split('#')[0]
            if ":" in rg:
                NORETRIEVE.append(rg)
            if ";" in rg:
                NORETRIEVE.append(rg)
            if "&" in rg:
                NORETRIEVE.append(rg)
            if "/" in rg:
                if not GETTRANSLATIONS:
                    NORETRIEVE.append(rg)
            pages.append(rg)
    return pages

def getimagelinks(html):
    "returns a list of image links found in an html file"
    return re.findall('<img.*?src="(.*?)"',html)

def cleanhtml(html):
    "cleans given html code from dirty script stuff"
    html = html.replace('\n','Wlinebreak') # removing linebreaks for regex processing
    html = re.compile('(.*)<div[^>]+column-content+[^>]+>').sub('',html) # stripping before content
    html = re.compile('<div[^>]+column-one+[^>]+>.*').sub('',html) # stripping after content
    html = re.compile('<!--[^>]+-->').sub('',html) # removing comment tags
    html = re.compile('<script[^>]*>.*?</script>').sub('',html) # removing script tags
    html = re.compile('<!--\[if[^>]*>.*?endif\]-->').sub('',html) # removing IE tags
    html = re.compile('<div id="jump-to-nav"[^>]*>.*?</div>').sub('',html) # removing nav div
    html = re.compile('<h3 id="siteSub"[^>]*>.*?</h3>').sub('',html) # removing print subtitle
    html = re.compile('Retrieved from').sub('Online version:',html) # changing online title
    html = re.compile('<div id="mw-normal-catlinks[^>]>.*?</div>').sub('',html) # removing catlinks
    html = re.compile('<div class="NavHead.*?</div>').sub('',html) # removing nav stuff
    html = re.compile('<div class="NavContent.*?</div>').sub('',html) # removing nav stuff
    html = re.compile('<div class="NavEnd.*?</div>').sub('',html) # removing nav stuff
    html = re.compile('<div class="docnav.*?</div></div>').sub('',html) # removing docnav
    if not GETTRANSLATIONS:
        html = re.compile('<div class="languages.*?</div>').sub('',html) # removing translations links
    html = re.compile('Wlinebreak').sub('\n',html) # restoring original linebreaks
    return html
    

def cleanlinks(html, pages=None):
    "cleans page links found in html"
    if not pages: pages = getlinks(html)
    for page in pages:
        if  page in NORETRIEVE:
            output = 'href="' + URL + wikiindex + page + '"'
        else:
            output = 'href="' + page.replace("/","-") + '.html"'
        html = re.compile('href="[^"]+' + page + '"').sub(output,html)
    return html

def cleanimagelinks(html,links=None):
    "cleans image links in given html"
    if not links: links = getimagelinks(html)
    if links:
        for l in links:
            nl = re.findall('.*/(.*)',l)
            if nl: html = html.replace(l,nl[0])
            # fetchimage(l)
    return html

def fetchpage(page):
    "retrieves given page from the wiki"
    failcount = 0
    while failcount < MAXFAIL:
        try:
            html = (urlopen(URL + wikiindex + page).read())
            return html
        except HTTPError:
            failcount += 1
    print 'Error: unable to fetch page ' + page

def fetchimage(imagelink):
    "retrieves given image from the wiki and saves it"
    if imagelink[0:5] == "File:":
        print "Skipping file page link"
        return
    filename = re.findall('.*/(.*)',imagelink)[0]
    print "saving",filename
    if not exists(filename,image=True):
        failcount = 0
        while failcount < MAXFAIL:
            try:
                if VERBOSE: print "Fetching " + filename
                data = (urlopen(webroot(URL) + imagelink).read())
                path = local(filename,image=True)
                file = open(path,'wb')
                file.write(data)
                file.close()
                processed.append(filename)
                return
            except:
                failcount += 1
        print 'Error: unable to fetch file ' + filename

def local(page,image=False):
    "returns a local path for a given page/image"
    if image:
        return FOLDER + os.sep + page
    else:
        return FOLDER + os.sep + page + '.html'

def exists(page,image=False):
    "checks if given page/image already exists"
    path = local(page.replace("/","-"),image)
    if os.path.exists(path): return True
    return False

def webroot(url):
    return re.findall('(http://.*?)/',url)[0]

def output(html,page):
    "encapsulates raw html code into nice html body"
    header = "<html><head>"
    header += "<title>"
    header += page
    header += "</title>"
    header += "<link type='text/css' href='wiki.css' rel='stylesheet'>"
    header += "</head><body>"
    footer = "</body></html>"
    html = header+html+footer
    filename = local(page.replace("/","-"))
    print "saving",filename
    file = open(filename,'wb')
    file.write(html)
    file.close()

if __name__ == "__main__":
	crawl()
      
Back to Top