Remove unnecessary spaces from document object’s page_content of Bili…

…BiliLoader (langchain-ai#4619) - Remove unnecessary spaces from document object’s page_content of BiliBiliLoader - Fix BiliBiliLoader document and test file
alps99w · May 16, 2023 · f7e3d97 · f7e3d97
1 parent f47ec5b
commit f7e3d97
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 8 deletions.
diff --git a/docs/modules/indexes/document_loaders/examples/bilibili.ipynb b/docs/modules/indexes/document_loaders/examples/bilibili.ipynb
@@ -5,7 +5,7 @@
    "id": "66a7777e",
    "metadata": {},
    "source": [
-    "# Bilibili\n",
+    "# BiliBili\n",
     "\n",
     ">[Bilibili](https://www.bilibili.tv/) is one of the most beloved long-form video sites in China.\n",
     "\n",
@@ -35,7 +35,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.document_loaders.bilibili import BiliBiliLoader"
+    "from langchain.document_loaders import BiliBiliLoader"
    ]
   },
   {

diff --git a/langchain/document_loaders/bilibili.py b/langchain/document_loaders/bilibili.py
@@ -60,11 +60,11 @@ def _get_bilibili_subs_and_info(self, url: str) -> Tuple[str, dict]:
             raw_sub_titles = json.loads(result.content)["body"]
             raw_transcript = " ".join([c["content"] for c in raw_sub_titles])
 
-            raw_transcript_with_meta_info = f"""
-                Video Title: {video_info['title']},
-                description: {video_info['desc']}\n
-                Transcript: {raw_transcript}
-                """
+            raw_transcript_with_meta_info = (
+                f"Video Title: {video_info['title']},"
+                f"description: {video_info['desc']}\n\n"
+                f"Transcript: {raw_transcript}"
+            )
             return raw_transcript_with_meta_info, video_info
         else:
             raw_transcript = ""

diff --git a/tests/integration_tests/document_loaders/test_bilibili.py b/tests/integration_tests/document_loaders/test_bilibili.py
@@ -1,4 +1,4 @@
-from langchain.document_loaders.bilibili import BiliBiliLoader
+from langchain.document_loaders import BiliBiliLoader
 
 
 def test_bilibili_loader() -> None: