Created
June 2, 2022 12:21
-
-
Save allatambov/a9e3ee4f52114e097cb5269aec467416 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
def get_info(my_link): | |
my_page = requests.get(my_link) | |
my_soup = BeautifulSoup(my_page.text) | |
author = my_soup.find("meta", | |
{"name" : "mediator_author"})["content"] | |
date = my_soup.find("meta", | |
{"itemprop" : "datePublished"})["content"] | |
title = my_soup.find("title").text | |
desc = my_soup.find("meta", | |
{"name" : "description"})["content"] | |
div = my_soup.find("div", {"class" : "tables"}) | |
tabs = div.find_all("p") | |
rubs_raw = tabs[0].find_all("a") | |
rubs = [r.text for r in rubs_raw] | |
rubs_str = ", ".join(rubs) | |
time = tabs[1].find("span").text | |
diffc = tabs[2].find("span", {"class" : "difficult-value"}).text | |
pars_raw = my_soup.find_all("p", {"class" : None}) | |
pars_str = [p.text for p in pars_raw] | |
text = " ".join(pars_str) | |
text = text.split("Нашли опечатку?")[0] | |
text = text.replace("\xa0", " ") | |
text = text.replace("\n", " ") | |
res = [title, desc, author, date, time, rubs_str, diffc, text] | |
return res |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment