Created
August 13, 2020 15:51
-
-
Save jmrobles/f80ed4686dd81660e5709c0a309a37a2 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
| def html2ScrapedWeb(url: str, html: str) -> ScrapedWebVitamined: | |
| """ | |
| Parse HTML using BS4 HTML5Lib parser and get <body> content without | |
| <nav>, <script>, <footer> | |
| It's focus on content | |
| """ | |
| dom = BeautifulSoup(html, 'html5lib') | |
| # 1. Get title | |
| title = dom.title.string if dom.title else None | |
| # 2. Get description | |
| desc = getDescription(dom) | |
| # 3. Remove undesired elements | |
| dropTags = ["script", "head", "nav", "footer"] | |
| for tag in dropTags: | |
| for elem in dom.find_all(tag): | |
| elem.decompose() | |
| # 4. Headings | |
| headings = [x.getText() for idx in range(6) for x in dom.find_all(f'h{idx+1}') if x] | |
| # 5. Content | |
| s = set() | |
| for x in dom.find_all(["p", "td", "li", "a"]): | |
| s.add(x.getText().strip()) | |
| contents = list(s) | |
| return ScrapedWebVitamined(url, title, desc, headings, contents, dom) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment