Skip to content

PALLADIUM26/skyScraper

Repository files navigation

skyScraper

This is like a side-quest for something big.

This project consists of codes for:

  1. Searching through google using Python
  2. Websraping using Python
  3. Summarizing paragraph using Gemini API

  • Import libraries for using Google
  • Searching according to some keyword
  • Search according to user input
  • Search according to some keyword and provide number links given by user
  • Remaining parts are related to websraping which will be discussed in the following section
  • Import libraries for webscraping
  • Get link through google with user given input
  • Send an HTTP request to the URL of the webpage you want to access
  • Parse the HTML content using BeautifulSoup
  • Extract the text content of the webpage
  • Print the text

3. Contents of Webscraping.ipynb

  • Import libraries for using Gemini API
  • Securely store your API key
  • Fetch an environment variable for API key
  • Load model Gemini-Pro
  • Search according to input given by user
  • Perform webscraping
  • Summarize the extracted text and display

4. Contents of websraper.py

  • Import libraries
  • Open webpage in default browser
  • Wait so that webpage is fully loaded
  • Use shortkeys for select all and copy automatically
  • Store copied content from clipboard in a variable

Import Libraries:

pip install -r requirements.txt

.py files are also provided

About

This is like a side-quest for something big.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published