def __parse(self, fragment):
content = KnowledgeParser.fetch_content(fragment)
if content is None:
return None
else:
self.id = content["id"]
self.title = content["title"]
self.wikitext = content["wikitext"]
categorylinks = self.fetch_categorylinks()
# remove the first pic and format the remaining pics
allpics = self.__remove_first_pic()
# remove category from wikitext
self.__remove_categories()
# wikitext -> html
self.wikitext = self.wikitext.strip()
body_html = parselite(self.wikitext)
output = {
"pic": allpics[0] if allpics else None,
"title": self.title,
"body": body_html,
"categorylinks": categorylinks
}
return output
def wiki(request):
user = users.get_current_user()
if user:
greeting = ("<a href=\"%s\">Sign Out</a>" %
(users.create_logout_url("/")))
else:
greeting = ("<a href=\"%s\">Sign in</a>" %
users.create_login_url("/"))
if users.is_current_user_admin():
show_edit = True
else:
show_edit = False
wikiz = models.Wiki.all()
for wiki in wikiz:
wiki_text=parselite(wiki.content)
payload = dict(wiki_text=wiki_text)
return render('wiki.html', payload)
def markup(value, parser):
esc = conditional_escape
if parser == 1:
import postmarkup
from pygments import highlight
from pygments.lexers import get_lexer_by_name, ClassNotFound
#from pygments.lexers import guess_lexer
from pygments.formatters import HtmlFormatter
markup = postmarkup.create(annotate_links=False,exclude=["img", "code"],use_pygments=False)
class ImgTag(postmarkup.TagBase):
valid_params = ("left", "right")
def __init__(self, name, **kwargs):
postmarkup.TagBase.__init__(self, name, inline=True)
def render_open(self, parser, node_index):
contents = self.get_contents(parser)
self.skip_contents(parser)
contents = postmarkup.strip_bbcode(contents).replace(u'"', "%22")
if self.params in self.valid_params:
return u'<img class="float-%s" src="%s" alt="%s">' % (self.params, contents, contents)
else:
return u'<img src="%s" alt="%s">' % (contents, contents)
class PygmentsCodeTag(postmarkup.TagBase):
def __init__(self, name, pygments_line_numbers=True, **kwargs):
postmarkup.TagBase.__init__(self, name, enclosed=True, strip_first_newline=True)
self.line_numbers = pygments_line_numbers
def render_open(self, parser, node_index):
contents = self.get_contents(parser)
self.skip_contents(parser)
#if self.params:
try:
lexer = get_lexer_by_name(self.params, stripall=True)
except ClassNotFound:
contents = postmarkup._escape_no_breaks(contents)
return '<div class="code"><pre>%s</pre></div>' % contents
#Well, do we realy need lexer gues?
#else:
# lexer = guess_lexer(contents)
formatter = HtmlFormatter(linenos='inline', cssclass="code")
return highlight(contents, lexer, formatter)
markup.add_tag(ImgTag, u'img')
markup.add_tag(PygmentsCodeTag, u'code')
markup.add_tag(postmarkup.SimpleTag, u'block', u'div class="mblock"')
value = "<p>" + markup(value) + "</p>"
return value
elif parser == 2:
from markdown import markdown
value = esc(value)
value = markdown(value)
return value
elif parser == 3:
from wikimarkup import parselite
value = parselite(value)
elif parser == 4:
from django.template.defaultfilters import removetags
value = removetags(value, 'style html script applet form frame iframe map noframes noscript object var area input button select')
value = linebreaks(value)
else:
value = esc(value)
value = urlize(value)
value = linebreaks(value)
return value
import json, re
import requests
from wikimarkup import parselite
def fetch_wikitext(url):
r = requests.get(url)
decode_json = json.loads(r.text)
wikitext = decode_json["query"]["pages"]["2"]["revisions"][0]["*"]
return wikitext
if __name__ == "__main__":
wikitext = fetch_wikitext("http://localhost/mediawiki/api.php?action=query&prop=revisions&rvprop=content&titles=HelloWorld&format=json")
print "======format: wikitext====="
print wikitext
print "======format: html========="
print parselite(wikitext)
picRegex = re.compile(r'[[File:(*) | *]]')
matchObj = picRegex.search(wikitext)
print matchObj.group(1)
