Created
February 18, 2022 20:09
-
-
Save bemitc/39989f589b44ae73f1143d2e95afac93 to your computer and use it in GitHub Desktop.
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
# Importing the libraries | |
from bs4 import BeautifulSoup | |
import requests | |
import sys | |
import re | |
import argparse | |
import os | |
import csv | |
# Function to generate cards using the given html page | |
def generateCards(htmlPage): | |
# Set the arrays | |
questionsData = [] | |
answersData = [] | |
# Loop the search for all of the questions, not only 30 (the Brainscape's questions limit by page) | |
i = 1 | |
while i < 5: | |
# Look for up to 5 possible pages | |
url = htmlPage + '?page=' + str(i) | |
# Fetch the raw HTML content | |
content = requests.get(url).text | |
# Parse the desired content | |
soup = BeautifulSoup(content, "lxml") | |
# Find the cards table | |
cardTable = soup.find('div', {'class': 'market-content'}) | |
# Find the questions and answers | |
questionsData += cardTable.find_all(attrs={'class': 'card-question-text'}) | |
answersData += cardTable.find_all(attrs={'class': 'card-answer-text'}) | |
i += 1 | |
if len(questionsData) == len(answersData): | |
with open('export.csv', 'w', newline='') as csvfile: | |
ankiExport=csv.writer(csvfile) | |
for x in range(len(questionsData)): | |
ankiExport.writerow([questionsData[x].get_text().strip(), answersData[x].get_text().strip().replace('>', '\n')]) | |
generateCards(sys.argv[1]) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment