initial

.gitignore

@@ -0,0 +1 @@
+venv

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+import requests
+from bs4 import BeautifulSoup
+import os
+import tempfile
+import re
+
+title = 'Web Scraper'
+description = '''
+'''
+
+
+def get_from_url(url):
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.content, 'html.parser')
+        text = soup.get_text(separator="\n")
+
+        with tempfile.NamedTemporaryFile(mode="w", delete=False, encoding="utf-8") as file:
+            filename = file.name
+            file.write(text)
+
+        return filename  # Return the temporary file path
+    except requests.exceptions.RequestException as e:
+        print("Error fetching the URL:", e)
+        return None
+    except Exception as e:
+        print("Error:", e)
+        return None
+
+
+def extract_text_from_html(urls):
+    return [get_from_url(url) for url in urls.split("\n")]
+
+
+interface = gr.Interface(fn=extract_text_from_html, inputs=[gr.Textbox(label="Url input")],
+                         outputs=[gr.File(label="Scrapped Text")], title=title,
+                         description=description)
+
+interface.launch(debug=True)

requirements.txt

@@ -0,0 +1,69 @@
+aiofiles==23.1.0
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.0.1
+annotated-types==0.5.0
+anyio==3.7.1
+async-timeout==4.0.2
+attrs==23.1.0
+beautifulsoup4==4.12.2
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.6
+contourpy==1.1.0
+cycler==0.11.0
+exceptiongroup==1.1.2
+fastapi==0.100.1
+ffmpy==0.3.1
+filelock==3.12.2
+fonttools==4.41.1
+frozenlist==1.4.0
+fsspec==2023.6.0
+gradio==3.39.0
+gradio_client==0.3.0
+h11==0.14.0
+httpcore==0.17.3
+httpx==0.24.1
+huggingface-hub==0.16.4
+idna==3.4
+Jinja2==3.1.2
+jsonschema==4.18.4
+jsonschema-specifications==2023.7.1
+kiwisolver==1.4.4
+linkify-it-py==2.0.2
+markdown-it-py==2.2.0
+MarkupSafe==2.1.3
+matplotlib==3.7.2
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+multidict==6.0.4
+numpy==1.25.1
+orjson==3.9.2
+packaging==23.1
+pandas==2.0.3
+Pillow==10.0.0
+pydantic==2.1.1
+pydantic_core==2.4.0
+pydub==0.25.1
+pyparsing==3.0.9
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3
+PyYAML==6.0.1
+referencing==0.30.0
+requests==2.31.0
+rpds-py==0.9.2
+semantic-version==2.10.0
+six==1.16.0
+sniffio==1.3.0
+soupsieve==2.4.1
+starlette==0.27.0
+toolz==0.12.0
+tqdm==4.65.0
+typing_extensions==4.7.1
+tzdata==2023.3
+uc-micro-py==1.0.2
+urllib3==2.0.4
+uvicorn==0.23.1
+websockets==11.0.3
+yarl==1.9.2