]> git.mxchange.org Git - fba.git/commitdiff
More logical Mastodon parsing order (fixes parsing pages with lots of <h3>)
authorMint <>
Fri, 2 Sep 2022 19:01:39 +0000 (22:01 +0300)
committerMint <>
Fri, 2 Sep 2022 19:01:39 +0000 (22:01 +0300)
fetch_blocks.py

index e2b5a3838f680b6220808190adc846b22197ba1f..50071b4ecb54ecc4d6f54ba903b738239e82f6d5 100644 (file)
@@ -39,11 +39,11 @@ def get_mastodon_blocks(domain: str) -> dict:
         return {}
 
     for header in doc.find_all("h3"):
-        for line in header.find_next_siblings("table")[0].find_all("tr")[1:]:
-            header_text = header.text
-            if header_text in translations:
-                    header_text = translations[header_text]
-            if header_text in blocks:
+        header_text = header.text
+        if header_text in translations:
+            header_text = translations[header_text]
+        if header_text in blocks:
+            for line in header.find_next_siblings("table")[0].find_all("tr")[1:]:
                 blocks[header_text].append(
                     {
                         "domain": line.find("span").text,