Check for dubious payloads

2020-12-03 10:12:09 +00:00 · 2020-12-03 10:12:09 +00:00 · 4f740a836c
parent 553bd86901
commit 4f740a836c
1 changed files with 4 additions and 0 deletions
--- a/newswire.py
+++ b/newswire.py
@ -227,10 +227,14 @@ def xml2StrToHashtagCategories(baseDir: str, domain: str, xmlStr: str,
        categoryStr = categoryStr.split('</title>')[0].strip()
        if not categoryStr:
            continue
+        if 'CDATA' in categoryStr:
+            continue
        hashtagListStr = rssItem.split('<description>')[1]
        hashtagListStr = hashtagListStr.split('</description>')[0].strip()
        if not hashtagListStr:
            continue
+        if 'CDATA' in hashtagListStr:
+            continue
        hashtagList = hashtagListStr.split(' ')
        if not isBlockedHashtag(baseDir, categoryStr):
            for hashtag in hashtagList: