Created
May 10, 2016 17:37
-
-
Save jheiselman/4fd5933c3d6895a21a23a22eaf553620 to your computer and use it in GitHub Desktop.
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
| #!/usr/bin/env python3 | |
| from html.parser import HTMLParser | |
| import requests | |
| class MyHTMLParser(HTMLParser): | |
| book_title = "" | |
| start_title_check = False | |
| grab_book_title = False | |
| def handle_starttag(self, tag, attrs): | |
| if tag == "div": | |
| for attr in attrs: | |
| if attr[0] == "class" and attr[1] == "dotd-title": | |
| #print("Starting title block check") | |
| self.start_title_check = True | |
| elif self.start_title_check == True and tag == "h2": | |
| #print("Starting book title grab") | |
| self.grab_book_title = True | |
| def handle_data(self, data): | |
| if self.grab_book_title == True: | |
| self.book_title = data.replace("\\n", "").replace("\\t", "") | |
| self.grab_book_title = False | |
| self.start_title_check = False | |
| url = "https://www.packtpub.com/packt/offers/free-learning" | |
| parser = MyHTMLParser() | |
| r = requests.get(url) | |
| parser.feed(str(r.content)) | |
| print(parser.book_title) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment