Created
March 3, 2021 16:38
-
-
Save typesupply/bbf314457dcda0c433a35f49508ec1a8 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
| from urllib.request import build_opener | |
| import bs4 | |
| from nltk.tokenize import PunktSentenceTokenizer | |
| # Pull some text from a Wikipedia entry. | |
| # The text could also come from a string, file or whatever. | |
| url = "https://en.wikipedia.org/wiki/Font,_Switzerland" | |
| opener = build_opener() | |
| opener.addheaders = [("User-agent", "Mozilla/5.0")] | |
| request = opener.open(url) | |
| html = request.read() | |
| request.close() | |
| try: | |
| soup = bs4.BeautifulSoup(html) | |
| except: | |
| print("[ERROR] Couldn't parse:", url) | |
| tags = ["p", "table", "td", "li", "dfn", "dd"] | |
| all = [] | |
| for tag in tags: | |
| for i in soup.find_all(tag): | |
| text = i.text | |
| if tag == "table": | |
| found = text.splitlines() | |
| else: | |
| found = [text] | |
| all.extend(found) | |
| text = "\n".join(all) | |
| # Extract sentences from the text. | |
| sentences = PunktSentenceTokenizer().tokenize(text) | |
| for sentence in sentences: | |
| print(sentence) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment