Last active
May 30, 2023 14:02
-
-
Save burkeholland/d001367a0dc047ef1c676124184d7455 to your computer and use it in GitHub Desktop.
scraper
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
# write a web scraper that will scrape CSS Tricks and FreeCodeCamp for all articles written by author Burke Holland | |
import requests | |
from bs4 import BeautifulSoup | |
import csv | |
# get the html from the page | |
page = requests.get("https://css-tricks.com/author/burkeholland/") | |
soup = BeautifulSoup(page.text, "html.parser") | |
# find all of the anchors on the page that are contained within a div with the class of "article-article | |
posts = soup.find_all("div", class_="article-article") | |
# loop over each blog post and display the title | |
for post in posts: | |
# get the title | |
h2 = post.find("h2") | |
anchor = h2.find("a") | |
print(anchor.get_text()) | |
# now for each post, get the contents of the article | |
articlePage = requests.get(anchor["href"]) | |
articleSoup = BeautifulSoup(articlePage.text, "html.parser") | |
# get the body of the article | |
articleBody = articleSoup.find(class_="article-content") | |
print(articleBody.get_text()) | |
# articlePage = requests.get(post.find("a")["href"]) | |
# articleSoup = BeautifulSoup(articlePage.text, "html.parser") | |
# # get the title | |
# title_element = articleSoup.find(class_="article-title") | |
# if title_element: | |
# title = title_element.get_text() | |
# else: | |
# title = "" | |
# print thte title | |
# print(title) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment