streamlit image

.gitignore

@@ -0,0 +1,128 @@
+flagged/
+test/
+
+# Editors
+.vscode/
+.idea/
+
+# Vagrant
+.vagrant/
+
+# Mac/OSX
+.DS_Store
+
+# Windows
+Thumbs.db
+
+# Source for the following rules: https://raw.githubusercontent.com/github/gitignore/master/Python.gitignore
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json

app.py

@@ -4,7 +4,7 @@ from PIL import Image
 from io import BytesIO
 
 def main():
-    st.title("Website Visualizer")
+    st.title("Website Content Exctractor")
     
     # Get website URL from user input
     url = st.text_input("Enter a URL:", "")
@@ -23,7 +23,7 @@ def visualize(url):
             innerHTML = take_screenshot(url)
             st.subheader("Website preview:")
             if innerHTML:
-                st.Image(innerHTML)
+                st.image(innerHTML)
             else:
                 st.error("Error: empty html")
     

extract.py

@@ -13,7 +13,7 @@ def take_screenshot(url):
         wd = webdriver.Chrome(options=options)
         wd.set_window_size(1080, 720)  # Adjust the window size here
         wd.get(url)
-        wd.implicitly_wait(10)
+        wd.implicitly_wait(5)
         screenshot = wd.get_screenshot_as_png()
     except WebDriverException as e:
         return Image.new('RGB', (1, 1))