Add filessupport, scrape and refine your data

Remove Webdriver usages Add continue messages for other providers
2025-12-24 13:07:53 +08:00 · 2025-01-01 04:20:02 +01:00
parent 90360ccfa6
commit 7893a0835e
33 changed files with 1155 additions and 559 deletions
--- a/setup.py
+++ b/setup.py
@@ -84,6 +84,16 @@ EXTRA_REQUIRE = {
    ],
    "local": [
        "gpt4all"
+    ],
+    "files": [
+        "spacy",
+        "filesplit",
+        "beautifulsoup4",
+        "pypdf2",
+        "docx",
+        "odfpy",
+        "ebooklib",
+        "openpyxl",
    ]
 }