This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import sys | |
import os | |
# example usage: python split.py example.csv 200 | |
# above command would split the `example.csv` into smaller CSV files of 200 rows each (with header included) | |
# if example.csv has 401 rows for instance, this creates 3 files in same directory: | |
# - `example_1.csv` (row 1 - 200) | |
# - `example_2.csv` (row 201 - 400) | |
# - `example_3.csv` (row 401) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import re | |
from bs4 import BeautifulSoup | |
from clint.textui import progress | |
# Url of the article | |
article_url = "https://towardsdatascience.com/springer-has-released-65-machine-learning-and-data-books-for-free-961f8181f189" | |
html_request = requests.get(article_url) | |
beautifulSoup = BeautifulSoup(html_request.content, "html.parser") |