Created
February 7, 2019 22:18
-
-
Save joshdabosh/a74d8ec1252a09c5fae2e6b878ec0561 to your computer and use it in GitHub Desktop.
Scrapes codecandies.com quotes and puts them into quotes.txt
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
from bs4 import BeautifulSoup as bs | |
import requests | |
page = requests.get("https://codecandies.com/") | |
soup = bs(page.content, "html.parser") | |
main = soup.find("div", {"class":"wrapper"}) | |
quotes = [] | |
for a in main.findAll("div", {"class":"section-inner"}): | |
for b in a.findAll("div", {"class":"posts"}): | |
for post in b.findAll("div", {"class": "post-container"}): | |
for post_inner in post.findAll("div", {"class": "type-post"}): | |
for post_content in post_inner.findAll("div", {"class": "post-content"}): | |
for blockquote in post_content.findAll("blockquote"): | |
for pre in blockquote.findAll("pre"): | |
quotes.append(pre.text.strip()) | |
with open("quotes.txt", "w") as f: | |
q = "\n\n".join(quotes) | |
f.write(q) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment