This file is indexed.

/usr/lib/python2.7/dist-packages/cssutils/script.py is in python-cssutils 1.0-4.1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
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
"""classes and functions used by cssutils scripts
"""
__all__ = ['CSSCapture', 'csscombine']
__docformat__ = 'restructuredtext'
__version__ = '$Id: parse.py 1323 2008-07-06 18:13:57Z cthedot $'

import HTMLParser
import codecs
import cssutils
import errno
import logging
import os
import sys
import urllib2
import urlparse

try:
    import cssutils.encutils as encutils
except ImportError:
    try:
        import encutils
    except ImportError:
        sys.exit("You need encutils from http://cthedot.de/encutils/")

# types of sheets in HTML
LINK = 0 # <link rel="stylesheet" type="text/css" href="..." [@title="..." @media="..."]/>
STYLE = 1 # <style type="text/css" [@title="..."]>...</style>

class CSSCaptureHTMLParser(HTMLParser.HTMLParser):
    """CSSCapture helper: Parse given data for link and style elements"""
    curtag = u''
    sheets = [] # (type, [atts, cssText])

    def _loweratts(self, atts):
        return dict([(a.lower(), v.lower()) for a, v in atts])

    def handle_starttag(self, tag, atts):
        if tag == u'link':
            atts = self._loweratts(atts)
            if u'text/css' == atts.get(u'type', u''):
                self.sheets.append((LINK, atts))
        elif tag == u'style':
            # also get content of style
            atts = self._loweratts(atts)
            if u'text/css' == atts.get(u'type', u''):
                self.sheets.append((STYLE, [atts, u'']))
                self.curtag = tag
        else:
            # close as only intersting <style> cannot contain any elements
            self.curtag = u''

    def handle_data(self, data):
        if self.curtag == u'style':
            self.sheets[-1][1][1] = data # replace cssText

    def handle_comment(self, data):
        # style might have comment content, treat same as data
        self.handle_data(data)

    def handle_endtag(self, tag):
        # close as style cannot contain any elements
        self.curtag = u''


class CSSCapture(object):
    """
    Retrieve all CSS stylesheets including embedded for a given URL.
    Optional setting of User-Agent used for retrieval possible
    to handle browser sniffing servers.

    raises urllib2.HTTPError
    """
    def __init__(self, ua=None, log=None, defaultloglevel=logging.INFO):
        """
        initialize a new Capture object

        ua
            init User-Agent to use for requests
        log
            supply a log object which is used instead of the default
            log which writes to sys.stderr
        defaultloglevel
            constant of logging package which defines the level of the
            default log if no explicit log given
        """
        self._ua = ua

        if log:
            self._log = log
        else:
            self._log = logging.getLogger('CSSCapture')
            hdlr = logging.StreamHandler(sys.stderr)
            formatter = logging.Formatter('%(message)s')
            hdlr.setFormatter(formatter)
            self._log.addHandler(hdlr)
            self._log.setLevel(defaultloglevel)
            self._log.debug(u'Using default log')

        self._htmlparser = CSSCaptureHTMLParser()
        self._cssparser = cssutils.CSSParser(log = self._log)

    def _doRequest(self, url):
        """Do an HTTP request

        Return (url, rawcontent)
            url might have been changed by server due to redirects etc
        """
        self._log.debug(u'    CSSCapture._doRequest\n        * URL: %s' % url)

        req = urllib2.Request(url)
        if self._ua:
            req.add_header('User-agent', self._ua)
            self._log.info('        * Using User-Agent: %s', self._ua)

        try:
            res = urllib2.urlopen(req)
        except urllib2.HTTPError, e:
            self._log.critical('    %s\n%s %s\n%s' % (
                e.geturl(), e.code, e.msg, e.headers))
            return None, None

        # get real url
        if url != res.geturl():
            url = res.geturl()
            self._log.info('        URL retrieved: %s', url)

        return url, res

    def _createStyleSheet(self, href=None,
                          media=None,
                          parentStyleSheet=None,
                          title=u'',
                          cssText=None,
                          encoding=None):
        """
        Return CSSStyleSheet read from href or if cssText is given use that.

        encoding
            used if inline style found, same as self.docencoding
        """
        if cssText is None:
            encoding, enctype, cssText = cssutils.util._readUrl(href, parentEncoding=self.docencoding)
            encoding = None # already decoded???

        sheet = self._cssparser.parseString(cssText, href=href, media=media, title=title,
                                            encoding=encoding)

        if not sheet:
            return None

        else:
            self._log.info(u'    %s\n' % sheet)
            self._nonparsed[sheet] = cssText
            return sheet

    def _findStyleSheets(self, docurl, doctext):
        """
        parse text for stylesheets
        fills stylesheetlist with all found StyleSheets

        docurl
            to build a full url of found StyleSheets @href
        doctext
            to parse
        """
        # TODO: ownerNode should be set to the <link> node
        self._htmlparser.feed(doctext)

        for typ, data in self._htmlparser.sheets:
            sheet = None

            if LINK == typ:
                self._log.info(u'+ PROCESSING <link> %r' % data)

                atts = data
                href = urlparse.urljoin(docurl, atts.get(u'href', None))
                sheet = self._createStyleSheet(href=href,
                                               media=atts.get(u'media', None),
                                               title=atts.get(u'title', None))
            elif STYLE == typ:
                self._log.info(u'+ PROCESSING <style> %r' % data)

                atts, cssText = data
                sheet = self._createStyleSheet(cssText=cssText,
                                               href = docurl,
                                               media=atts.get(u'media', None),
                                               title=atts.get(u'title', None),
                                               encoding=self.docencoding)
                if sheet:
                    sheet._href = None # inline have no href!
                print sheet.cssText

            if sheet:
                self.stylesheetlist.append(sheet)
                self._doImports(sheet, base=docurl)


    def _doImports(self, parentStyleSheet, base=None):
        """
        handle all @import CSS stylesheet recursively
        found CSS stylesheets are appended to stylesheetlist
        """
        # TODO: only if not parsed these have to be read extra!

        for rule in parentStyleSheet.cssRules:
            if rule.type == rule.IMPORT_RULE:
                self._log.info(u'+ PROCESSING @import:')
                self._log.debug(u'    IN: %s\n' % parentStyleSheet.href)
                sheet = rule.styleSheet
                href = urlparse.urljoin(base, rule.href)
                if sheet:
                    self._log.info(u'    %s\n' % sheet)
                    self.stylesheetlist.append(sheet)
                    self._doImports(sheet, base=href)

    def capture(self, url):
        """
        Capture all stylesheets at given URL's HTML document.
        Any HTTPError is raised to caller.

        url
            to capture CSS from

        Returns ``cssutils.stylesheets.StyleSheetList``.
        """
        self._log.info(u'\nCapturing CSS from URL:\n    %s\n', url)
        self._nonparsed = {}
        self.stylesheetlist = cssutils.stylesheets.StyleSheetList()

        # used to save inline styles
        scheme, loc, path, query, fragment = urlparse.urlsplit(url)
        self._filename = os.path.basename(path)

        # get url content
        url, res = self._doRequest(url)
        if not res:
            sys.exit(1)

        rawdoc = res.read()

        self.docencoding = encutils.getEncodingInfo(
            res, rawdoc, log=self._log).encoding
        self._log.info(u'\nUsing Encoding: %s\n', self.docencoding)

        doctext = rawdoc.decode(self.docencoding)

        # fill list of stylesheets and list of raw css
        self._findStyleSheets(url, doctext)

        return self.stylesheetlist

    def saveto(self, dir, saveraw=False, minified=False):
        """
        saves css in "dir" in the same layout as on the server
        internal stylesheets are saved as "dir/__INLINE_STYLE__.html.css"

        dir
            directory to save files to
        saveparsed
            save literal CSS from server or save the parsed CSS
        minified
            save minified CSS

        Both parsed and minified (which is also parsed of course) will
        loose information which cssutils is unable to understand or where
        it is simple buggy. You might to first save the raw version before
        parsing of even minifying it.
        """
        msg = 'parsed'
        if saveraw:
            msg = 'raw'
        if minified:
            cssutils.ser.prefs.useMinified()
            msg = 'minified'

        inlines = 0
        for i, sheet in enumerate(self.stylesheetlist):
            url = sheet.href
            if not url:
                inlines += 1
                url = u'%s_INLINE_%s.css' % (self._filename, inlines)

            # build savepath
            scheme, loc, path, query, fragment = urlparse.urlsplit(url)
            # no absolute path
            if path and path.startswith('/'):
                path = path[1:]
            path = os.path.normpath(path)
            path, fn = os.path.split(path)
            savepath = os.path.join(dir, path)
            savefn = os.path.join(savepath, fn)
            try:
                os.makedirs(savepath)
            except OSError, e:
                if e.errno != errno.EEXIST:
                    raise e
                self._log.debug(u'Path "%s" already exists.', savepath)

            self._log.info(u'SAVING %s, %s %r' % (i+1, msg, savefn))

            sf = open(savefn, 'wb')
            if saveraw:
                cssText = self._nonparsed[sheet]
                uf = codecs.getwriter('css')(sf)
                uf.write(cssText)
            else:
                sf.write(sheet.cssText)
            sf.close()

def csscombine(path=None, url=None, cssText=None, href=None,
               sourceencoding=None, targetencoding=None, 
               minify=True, resolveVariables=True):
    """Combine sheets referred to by @import rules in given CSS proxy sheet
    into a single new sheet.

    :returns: combined cssText, normal or minified
    :Parameters:
        `path` or `url` or `cssText` + `href`
            path or URL to a CSSStyleSheet or a cssText of a sheet which imports
            other sheets which are then combined into one sheet.
            `cssText` normally needs `href` to be able to resolve relative
            imports.
        `sourceencoding` = 'utf-8'
            explicit encoding of the source proxysheet
        `targetencoding`
            encoding of the combined stylesheet
        `minify` = True
            defines if the combined sheet should be minified, in this case
            comments are not parsed at all!
        `resolveVariables` = True
            defines if variables in combined sheet should be resolved
    """
    cssutils.log.info(u'Combining files from %r' % url, 
                      neverraise=True)
    if sourceencoding is not None:
        cssutils.log.info(u'Using source encoding %r' % sourceencoding,
                          neverraise=True)
        
    parser = cssutils.CSSParser(parseComments=not minify)
        
    if path and not cssText:
        src = parser.parseFile(path, encoding=sourceencoding)
    elif url:
        src = parser.parseUrl(url, encoding=sourceencoding)
    elif cssText:
        src = parser.parseString(cssText, href=href, encoding=sourceencoding)
    else:
        sys.exit('Path or URL must be given')

    result = cssutils.resolveImports(src)
    result.encoding = targetencoding
    cssutils.log.info(u'Using target encoding: %r' % targetencoding, neverraise=True)

    oldser = cssutils.ser
    cssutils.setSerializer(cssutils.serialize.CSSSerializer())
    if minify:
        cssutils.ser.prefs.useMinified()
    cssutils.ser.prefs.resolveVariables = resolveVariables
    cssText = result.cssText
    cssutils.setSerializer(oldser)
    
    return cssText