From acc1822adaf9ef4e9ea6b16b77c6601c55d9a216 Mon Sep 17 00:00:00 2001
From: yumoqing <yumoqing@gmail.com>
Date: Thu, 30 Jul 2026 18:26:16 +0800
Subject: [PATCH] =?UTF-8?q?=E7=A7=BB=E9=99=A4=20langchain=5Fcommunity=20?=
 =?UTF-8?q?=E4=BE=9D=E8=B5=96=EF=BC=8C=E5=86=85=E8=81=94=20CSVLoader/TextL?=
 =?UTF-8?q?oader=EF=BC=8C=E5=8F=AF=E9=80=89=E5=8C=96=20ebooklib/bs4/mobi/h?=
 =?UTF-8?q?tml2text=20=E5=AF=BC=E5=85=A5?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 filetxt/loader.py | 62 +++++++++++++++++++++++++++++------------------
 1 file changed, 39 insertions(+), 23 deletions(-)

diff --git a/filetxt/loader.py b/filetxt/loader.py
index 1d05bfd..ee66538 100644
--- a/filetxt/loader.py
+++ b/filetxt/loader.py
@@ -1,16 +1,31 @@
 import os
+import csv
 import codecs
 from datetime import datetime
-from langchain_community.document_loaders.csv_loader import CSVLoader
-from langchain_community.document_loaders.text import TextLoader
 from docx import Document
-from ebooklib import epub
-from bs4 import BeautifulSoup
 from pptx import Presentation
 from openpyxl import load_workbook
-import mobi
 from pypdf import PdfReader
-import html2text
+
+try:
+    from ebooklib import epub
+except ImportError:
+    epub = None
+
+try:
+    from bs4 import BeautifulSoup
+except ImportError:
+    BeautifulSoup = None
+
+try:
+    import mobi
+except ImportError:
+    mobi = None
+
+try:
+    import html2text
+except ImportError:
+    html2text = None
 
 class BaseLoader:
 	def __init__(self, file_path):
@@ -26,11 +41,15 @@ class BaseLoader:
 		raise Exception('Not implement')
 			
 class MyMobiLoader(BaseLoader):
-	def load_pagetext(self):
-		tempdir, filepath = mobi.extract(self.filepath)
-		with codecs.open(filepath, "r", "utf-8") as f:
-			content=f.read()
-			yield (0, html2text.html2text(content))
+    def load_pagetext(self):
+        if mobi is None:
+            raise ImportError("mobi not installed. Run: pip install mobi")
+        if html2text is None:
+            raise ImportError("html2text not installed. Run: pip install html2text")
+        tempdir, filepath = mobi.extract(self.filepath)
+        with codecs.open(filepath, "r", "utf-8") as f:
+            content=f.read()
+            yield (0, html2text.html2text(content))
 		
 class MyPdfLoader(BaseLoader):
 	def load_pagetext(self):
@@ -59,12 +78,11 @@ class MyPptLoader(BaseLoader):
 			yield (i,'\n'.join(txts))
 
 class MyCsvLoader(BaseLoader):
-	def load_pagetext(self):
-		loader = CSVLoader(self.filepath)
-		docs = loader.load()
-		for i, d in enumerate(docs):
-			dat = (i, d.page_content) 
-			yield dat
+    def load_pagetext(self):
+        with open(self.filepath, 'r', newline='', encoding='utf-8') as f:
+            reader = csv.reader(f)
+            for i, row in enumerate(reader):
+                yield (i, '	'.join(row))
 
 class MyExcelLoader(BaseLoader):
 	def load_pagetext(self):
@@ -97,12 +115,10 @@ class MyEpubLoader(BaseLoader):
 
 
 class MyTextLoader(BaseLoader):
-	def load_pagetext(self):
-		loader = TextLoader(self.filepath)
-		docs = loader.load()
-		for i, d in enumerate(docs):
-			dat = (i, d.page_content) 
-			yield dat
+    def load_pagetext(self):
+        with open(self.filepath, 'r', encoding='utf-8') as f:
+            content = f.read()
+        yield (0, content)
 
 class File2Text:
 	all_loaders = {