use the contents with html tags to generate the xml file

1 files changed, 37 insertions, 51 deletions

diff --git a/wiki_to_nitrate_xml.py b/wiki_to_nitrate_xml.py
index b473eab..c1706c5 100755
--- a/wiki_to_nitrate_xml.py
+++ b/wiki_to_nitrate_xml.py
@@ -7,6 +7,7 @@ import re
 import time, datetime
 import xml.etree.ElementTree as ET
 import xml.dom.minidom
+from BeautifulSoup import BeautifulSoup
 
 try:
     from simplemediawiki import MediaWiki
@@ -64,20 +65,12 @@ def parse_args():
 
 def parse(wiki, page):
     '''Parse a page and return content'''
-
-    # Build query arguments and call wiki
-    query = dict(action='query',
-		 prop='revisions',
-		 titles=page,
-                 rvprop='content')
+    query = dict(action='parse',
+                 page=page)
     if opts.debug: print query
     response = wiki.call(query)
-    for page in response.get('query',{}).get('pages',{}).values():
-        revs = page.get('revisions',[])
-        for t in revs:
-            return t.get('*','')
-    return ''
-
+    if opts.debug: print response
+    return response.get('parse',{})
 
 def list_categorymembers(wiki, cat_page, limit=5):
     '''Return a list of pages belonging to category page'''
@@ -108,64 +101,57 @@ def list_categorymembers(wiki, cat_page, limit=5):
 
     return members
 
-def extract(s, titles):
-    w_dsc = s.find('|description=')
-    w_setup = s.find('|setup=')
-    w_action = s.find('|actions=')
-    w_result = s.find('|results=')
-    w_resultend = s.find('}}')
-    start = [w_resultend+1, w_resultend+1]
+def extract_html(string, titles):
+    '''extract wiki contents in html format and cache to table'''
+    s_text = string.get('text',{}).get('*','')
+    s_tag = string.get('categories',{})
     tag = []
-    w_tagstart = []
-    w_tagend = []
-    i = 0
-    while True:
-        #saved '[[' and ']]' to w_tagstart and w_tagend separately. 
-        w_tagstart.append(s.find('[[', start[0]))
-        w_tagend.append(s.find(']]', start[1]))
-        if w_tagstart[i] == -1:
-            break
-	#saved category names to tag. 
-        tag.append(s[(w_tagstart[i]+len('[[Category:')):w_tagend[i]])
-        start[0] = w_tagstart[i] + 1
-        start[1] = w_tagend[i] + 1
-        i += 1
+    for t in s_tag:
+    	tag.append(t.get('*',''))
+    soup = BeautifulSoup(''.join(s_text))
     table = {}
     table['title'] = titles
-    if w_setup == -1:
-       table['description'] = s[(w_dsc+len('|description=')):w_action]
-       table['setup'] = ''
+    if soup.find(id='Description') == None:
+        table['description'] = ''
+    else:
+        table['description'] = soup.find(id='Description').findNext('p')
+    if soup.find(id='Setup') == None:
+        table['setup'] = ''
     else:
-       table['description'] = s[(w_dsc+len('|description=')):w_setup]
-       table['setup'] = s[(w_setup+len('|setup=')):w_action]
-    table['actions'] = s[(w_action+len('|actions=')):w_result]
-    table['results'] = s[(w_result+len('|results=')):w_resultend]
-    table['tag'] = tag
+        table['setup'] = soup.find(id='Setup').findNext('ol')    
+    table['actions'] = soup.find(id='How_to_test').findNext('ol')
+    table['results'] = soup.find(id='Expected_Results').findNext('ol')
+    table['tag'] = tag 
     return table
 
 def nitratexml(table):
-    #generate Nitrate format xml for wiki test case
+    '''generate Nitrate format xml from wiki test case'''
     root = ET.Element("testopia")
     root.attrib["version"] = "1.1"
     head = ET.SubElement(root, "testcase")
+    head.attrib["author"] = "rhe@redhat.com"
+    head.attrib["priority"] = "P1"
+    head.attrib["automated"] = ""
+    head.attrib["status"] = "PROPOSED"
     title = ET.SubElement(head, "summary")
     title.text = table['title']
     title = ET.SubElement(head, "categoryname")
+    title.text = "default"
     title = ET.SubElement(head, "defaulttester")
     title = ET.SubElement(head, "notes")
-    title.text = table['description']
+    title.text = str(table['description'])
     title = ET.SubElement(head, "testplan_reference")
     title.attrib["type"] = "xml_description"
     title.text = "Fedora 15 Install Test Plan"
     title = ET.SubElement(head, "action")
-    title.text = table['actions']
+    title.text = str(table['actions'])
     title = ET.SubElement(head, "expectedresults")
-    title.text = table['results']
+    title.text = str(table['results'])
     title = ET.SubElement(head, "setup")
-    title.text = table['setup']
+    title.text = str(table['setup'])
     title = ET.SubElement(head, "breakdown")
     title = ET.SubElement(head, "tag")
-    title.text = table['tag'][0]
+    title.text = str(table['tag'][0])
     
     tree = ET.ElementTree(root)
     tree.write("output.xml", encoding="UTF-8", xml_declaration=True)
@@ -189,13 +175,13 @@ if __name__ == "__main__":
                 print "No data found for '%s'" % cat_page
  
     elif action == 'migration':
-        s =  parse(wiki, opts.title)
-        table = extract(s, opts.title)
+        string =  parse(wiki, opts.title)
+        table = extract_html(string, opts.title)
         if opts.debug: 
             for key in table.keys():
            	print key, '\t', table[key]
- 	pretty_xml_print = nitratexml(table)
-	print pretty_xml_print
+ 	pretty_xml_print = nitratexml(table) 
+	print pretty_xml_print, '\n', '\"The xml file named output.xml is generated at ./\"' 
     else:
 	print "Unknown action requested '%s'" % action