OneNewDev/Tagger
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

exclude code blocks

Browse source
This commit is contained in:
OneNewDev 2022-06-06 12:17:02 +02:00
parent 6a68caca90
commit 0c6c621919
1 changed files with 6 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
tagger.py
View file

@ -13,6 +13,7 @@ SOURCE_FILENAME = 'index.txt'
OUTPUT_FILE = 'tags.json'
TAGS_PER_ARTICLE = 5
JSON_INDENT = 2
EXCLUDED_HTML_TAGS = {'code'}
# Wegen Performance vordefinierte Variablen
_UPPER_CHECK = re.compile(r'[A-Z]')
@ -29,6 +30,7 @@ class FileScanner(HTMLParser):
super().__init__()
self.file = file
self.texte = []
self._current_html_tag = None
def scan_file(self):
# Datei einlesen
@ -86,6 +88,7 @@ class FileScanner(HTMLParser):
return sorted(words_with_usage.values(), key=lambda tag: tag.score, reverse=True)
def handle_starttag(self, tag, attrs):
self._current_html_tag = tag
# Die Links, die in den 'href' Attributen eines <a> HTML-Elements stehen, mit einbeziehen.
if tag != "a":
return
@ -95,8 +98,9 @@ class FileScanner(HTMLParser):
break
def handle_data(self, data):
# Den Text innerhalb eines HTML-Elements mit einbeziehen.
self.texte.append(data)
if self._current_html_tag not in EXCLUDED_HTML_TAGS:
# Den Text innerhalb eines HTML-Elements mit einbeziehen.
self.texte.append(data)
def display_tags(tags, min_score):