Created
May 9, 2021 12:11
-
-
Save nileshevrywhr/e03df96c7cc7d28ef813c66a395d8efe to your computer and use it in GitHub Desktop.
save the free daily blinkist offline in markdown format
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 | |
from bs4 import BeautifulSoup | |
host = "https://www.blinkist.com" | |
headers = {"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0"} | |
free_daily = requests.get("https://www.blinkist.com/en/nc/daily", headers=headers) | |
html = BeautifulSoup(free_daily.content, 'html.parser') | |
headline = html.find("h3", class_="daily-book__headline").get_text() | |
author = html.find(class_="daily-book__author") | |
link = html.find("a", class_="cta cta--play daily-book__cta").get('href') | |
slug = link.split("/")[-1] | |
article = requests.get(host + link, headers=headers) | |
soup = BeautifulSoup(article.content, 'html.parser') | |
chapters = soup.find_all('div', class_='chapter') | |
with open(slug + ".md", 'a') as f: | |
for chapter in chapters: | |
heading = chapter.find('h1').get_text() | |
f.write('#' + heading + '\n') | |
content = chapter.find_all(class_="chapter__content") | |
for paragraph in content: | |
f.write(paragraph.text + '\n') | |
f.write('\n') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment