Changeset 1916

Timestamp:

08/03/07 14:06:56 (5 years ago)

Author:

gabor

Message:

ref #738 spent 18h, Added support to href attributes. Links to downloaded files points to the proper downloaded file, links to the LeMill site are deleted and links to external site are kept intact. It is now possible to navigate from the collection's html file to its members' html file.

Files:

• trunk/Collection.py (modified) (15 diffs)

trunk/Collection.py

@@ -499 +499 @@
-
-#Zip / SCORM download stuff begin --------------------------------------------------------------------------------
-
+, pageURL
-
-        def flatten(seq):
@@ -526 +526 @@
-                elif previousInfo == None:
-                    previousInfo = ''
-+
-+
+ + 
+ + 
-            if previousInfo == None:
-                infoList.insert(0, None)
@@ -552 +552 @@
-            return inputList, infoList
-
-2, 4
+1, 2
-        if len(splitHtml) > 1:
-            baseURL = splitHtml[-2]
@@ -558 +558 @@
-            del infoList[1::2]
-        else:
-self.portal_url()
+pageURL
-        if not baseURL.endswith('/'):
-            baseURL += '/'
-
+
+
+
-        splitHtml, infoList = reqursiveRegularSplit(splitHtml, infoList, 'fvars', '(<embed[^>]*?flashvars=")(.*?)(")', 2, 4)
-)(src=")(.*?)(")', 3, 5
-)(src=")(.*?)(")', 3, 5
+src=")(.*?)(")', 2, 4
+src=")(.*?)(")', 2, 4
-        splitHtml, infoList = reqursiveRegularSplit(splitHtml, infoList, 'src', '(<param.+?name="movie".*?value=")(.*?)(")', 2, 4)
-        splitHtml, infoList = reqursiveRegularSplit(splitHtml, infoList, 'fvars', r"(<script.*?>.*?AC_FL_RunContent\(.*?'flashvars', ')(.*?)((?<!\\)'.*?</script>)", 2, 4)
@@ -572 +574 @@
-        return flatten(splitHtml), flatten(infoList), baseURL
-
-None
+''
-        flash = None
-
-
-
-
-
+
+
+
-            if info == 'jsfname':
-2
+
-        elif info == 'fvars':
-            if url.startswith('file='):
-2
+
-                flash = 'mp3'
-            elif url.startswith('xml='):
-2
+
-                flash = 'pilot'
-            elif url.startswith("config={videoFile: '"):
-2
+
-                flash = 'flv1'
-            elif url.startswith("config={videoFile: \\'"):
-2
+
-                flash = 'flv2'
-
-
-
-
+
+
+
+
+
+
+
+
-
-    def _hasFileNameInSrcs(self, fileName, srcs):
@@ -603 +607 @@
-            src = srcs[absURL]
-            if src.has_key('fileName') and src['fileName'] == fileName:
-
-
-
-
-
-
-
-
+
+
-
-    def _findUniqueFileName(self, absURL, srcs):
-
-
-
+
+
+
+
+
-            src2['counter'] += 1
-            fileName, extension = self._splitFileName(fileName)
-            return self._findUniqueFileName('%s(%d)%s' % (fileName, src2['counter'], extension), srcs)
-
-
-
-
+
+
-        for i in range(len(infoList)):
-
+, 'href'
-                absURL, flash = self._getAbsoluteURL(splitHtml[i], infoList[i], baseURL)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
-                    else:
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-                else:
-
+
+
+
+
+
-
-    def _processPilotXMLs(self, srcs, baseURLs, baseDirs):
@@ -653 +662 @@
-                src = srcs[absURL]
-                file = urlopen(absURL)
-                #file = urlopen('http://localhost:81/buildXML.xml')
-                xml = file.read().decode('utf-16')
-                file.close()
-                xmlDatas[absURL]={}
-                xmlData = xmlDatas[absURL]
-
+, ''
-                xmlData['fileName'] = src['fileName']
-                xmlData['baseDirs'] = []
-                for htmlIndex in src['usedBy']:
-
+{}, 
-                    xmlData['baseDirs'].append(baseDirs[htmlIndex])
-            except (HTTPError, URLError):
@@ -668 +676 @@
-        return xmlDatas
-
-    def _addExtension(self, fileName, extension):
-        name, ext = self._splitFileName(fileName)
-        if ext == '' and extension != '':
-            fileName = '%s.%s' % (fileName, extension)
-        return fileName
-
-    def _downloadFiles(self, srcs, zip, baseDirs = []):
+        def _addExtension(fileName, extension):
+            name, ext = self._splitFileName(fileName)
+            if ext == '' and extension != '':
+                fileName = '%s.%s' % (fileName, extension)
+            return fileName
-        for absURL in srcs:
-            src = srcs[absURL]
-            data = ''
+            mediaType = ''
-            subType = ''
-            try:
@@ -683 +691 @@
-                    file = urlopen(absURL)
-                    data = file.read()
+                    mediaType, subType = file.headers.getheader('Content-Type').split('/')
-                    file.close()
-                    mediaType, subType = file.headers.getheader('Content-Type').split('/')
-                    subType = subType.split(';')[0]
-                    if mediaType == 'image':
-== 'jpeg'
+in ('jpeg', 'pjpeg')
-                           src['extension'] = 'jpg'
-
+
+
+
-                            src['extension'] = subType
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-            except (HTTPError, URLError):
-                print "File download error: " + absURL
-
-self.
+
-            if len(src['usedBy']) > 1:
-                src['finalURL'] = '_SharedFiles/' + fileName
-                if src['extension'] != 'xml':
-                    zip.writestr((src['finalURL']).encode('latin-1'), data)
-                src['finalURL'] = '../../' + src['finalURL']
-            else:
-                src['finalURL'] = '_Files/' + fileName
@@ -707 +730 @@
-                        zip.writestr((baseDirs[i] + src['finalURL']).encode('latin-1'), data)
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-        for i in range(len(splitHtmls)):
-            splitHtml = splitHtmls[i]
@@ -714 +761 @@
-                if infoList[j] in ('src', 'jsfname', 'fvars'):
-                    absURL, flash = self._getAbsoluteURL(splitHtml[j], infoList[j], baseURLs[i])
+                    src = srcs[absURL]
+                    if baseDirs[i] != '' and len(src['usedBy']) > 1:
+                        finalURL = '../../' + src['finalURL']
+                    else:
+                        finalURL = src['finalURL']
-                    if infoList[j] == 'src':
-srcs[absURL]['finalURL']
+finalURL
-                    elif infoList[j] == 'jsfname':
-srcs[absURL]['finalURL']
+finalURL
-                    elif infoList[j] == 'fvars':
-                        if flash == 'mp3':
-srcs[absURL]['finalURL']
+finalURL
-                        elif flash == 'pilot':
-srcs[absURL]['finalURL']
+finalURL
-                        elif flash == 'flv1':
-srcs[absURL]['finalURL']
+finalURL
-                        elif flash == 'flv2':
-
+
+
+
+
+
+
+
+
+
+
+
+
-
-    def _updatePilotXMLs(self, xmlDatas, baseURLs, srcs):
@@ -735 +798 @@
-                if xmlInfoList[j] in ('src', 'XMLmp3'):
-                    absURL2, flash = self._getAbsoluteURL(splitXML[j], xmlInfoList[j])
-
+
+
+
+
+
-
-    def _addHtmlsToZip(self, splitHtmls, zip, baseDirs = None):
@@ -760 +827 @@
-        baseURLs = []
-        baseDirs = []
+        htmlURLs = []
-        srcs = {}
+        hrefs = {}
-        htmlIndex = 0
-        resourceTypes = ('Content', 'Methods', 'Tools')
@@ -767 +836 @@
-            for resource in self.getResources(reftype = 'related%s' % resourceType):
-                htmlList.append((resource, '%s/%s/' % (resourceType.lower(), resource.getId())))
-
+
-        for html in htmlList:
-
+, self.portal_url()
-            splitHtmls.append(splitHtml)
-            infoLists.append(infoList)
-            baseURLs.append(baseURL)
-            baseDirs.append(html[1])
-
+
+
-            htmlIndex += 1
-
@@ -781 +851 @@
-        zip = zipfile.ZipFile(zipStr, 'w', compression = zipfile.ZIP_DEFLATED)
-        self._downloadFiles(srcs, zip, baseDirs)
-
+
+
-        self._updatePilotXMLs(xmlDatas, baseURLs, srcs)
-        self._addHtmlsToZip(splitHtmls, zip, baseDirs)