Created
September 3, 2019 22:42
-
-
Save wcneill/e1026122216e954cd9c0f463850e4271 to your computer and use it in GitHub Desktop.
Parses a Vanity Fair URL, prints article content to file
This file contains hidden or 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 | |
import requests as req | |
import textwrap as tr | |
# Iterates through all paragraph tags containing article content | |
# and formats content such that paragraphs are separated and all | |
# lines are no more than 72 characters in width. The .strings | |
# attribute of BS4 Tags returns a generator containing all text | |
# children of the given tag. In order to format the code | |
# using string.join, the generator needed to be converted to a | |
# list. | |
if __name__ == '__main__': | |
url = 'http://www.vanityfair.com/society/2014/06/monica-lewinsky-humiliation-culture' | |
r = req.get(url) | |
r_html = r.text | |
soup = BeautifulSoup(r_html, 'html.parser') | |
with open('html_to_text.txt', 'w') as open_file: | |
# get all divs with CSS class 'grid--item body body__container article__body grid-layout__content' | |
# then iterate through each paragraph in each div, format and print to file. | |
for stuff in soup.find_all('div', class_='grid--item body body__container article__body grid-layout__content'): | |
for par in stuff.find_all('p'): | |
text = list(par.strings) | |
open_file.write(tr.fill(" ".join(text), 72) + '\n') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment