community[patch]: fix bilibili loader handling of multi-page content (#30283)

Previously the loader would only extract subtitles from the first page
of multi-page videos.

libs/community/langchain_community/document_loaders/bilibili.py

@@ -11,6 +11,7 @@ from langchain_community.document_loaders.base import BaseLoader
 # Pre-compile regular expressions for video ID extraction
 BV_PATTERN = re.compile(r"BV\w+")
 AV_PATTERN = re.compile(r"av[0-9]+")
+PAGE_INDEX_PATTERN = re.compile(r"p=(\d+)")
 
 
 class BiliBiliLoader(BaseLoader):
@@ -93,8 +94,17 @@ class BiliBiliLoader(BaseLoader):
         if not self.credential:
             return "", video_info
 
+        cid = 0
+        page_match = PAGE_INDEX_PATTERN.search(url)
+        if page_match:
+            cid = video_info["pages"][int(page_match.group(1)) - 1][
+                "cid"
+            ]  # Bilibili page index starts from 1
+        else:
+            cid = video_info["cid"]
+
         # Fetching and processing subtitles
-        sub = sync(v.get_subtitle(video_info["cid"]))
+        sub = sync(v.get_subtitle(cid))
         sub_list = sub.get("subtitles", [])
         if sub_list:
             sub_url = sub_list[0].get("subtitle_url", "")

libs/community/tests/integration_tests/document_loaders/test_bilibili.py

@@ -7,9 +7,12 @@ def test_bilibili_loader() -> None:
         [
             "https://www.bilibili.com/video/BV1xt411o7Xu/",
             "https://www.bilibili.com/video/av330407025/",
+            "https://www.bilibili.com/video/BV16b4y1R7wP/?p=5",
         ]
     )
     docs = loader.load()
-    assert len(docs) == 2
+    assert len(docs) == 3
     assert docs[0].metadata["aid"] == 34218168
     assert docs[1].metadata["videos"] == 1
+    assert docs[2].metadata["pages"][5 - 1]["cid"] == 300059803
+    assert docs[2].metadata["cid"] == 300048569

libs/community/uv.lock

@@ -1,4 +1,5 @@
 version = 1
+revision = 1
 requires-python = ">=3.9, <4.0"
 resolution-markers = [
     "python_full_version >= '3.12.4' and platform_python_implementation == 'PyPy'",
@@ -1530,6 +1531,7 @@ requires-dist = [
     { name = "requests", specifier = ">=2,<3" },
     { name = "sqlalchemy", specifier = ">=1.4,<3" },
 ]
+provides-extras = ["community", "anthropic", "openai", "cohere", "google-vertexai", "google-genai", "fireworks", "ollama", "together", "mistralai", "huggingface", "groq", "aws", "deepseek", "xai"]
 
 [package.metadata.requires-dev]
 codespell = [{ name = "codespell", specifier = ">=2.2.0,<3.0.0" }]
@@ -1744,7 +1746,7 @@ typing = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.41"
+version = "0.3.45"
 source = { editable = "../core" }
 dependencies = [
     { name = "jsonpatch" },
@@ -1802,7 +1804,7 @@ typing = [
 
 [[package]]
 name = "langchain-tests"
-version = "0.3.13"
+version = "0.3.14"
 source = { editable = "../standard-tests" }
 dependencies = [
     { name = "httpx" },