David Zywiec
afb94de271
Add web scraping and summarization script using Playwright and OpenAI
...
This script allows users to input a URL, scrape the visible content using the Playwright framework, and summarize it using the OpenAI GPT-4o API. The summarized output is saved as a Markdown (.md) file, providing a clean and accessible format.
Key features:
- Prompts user for a URL at runtime
- Uses Playwright to scrape the page content
- Extracts visible text with BeautifulSoup
- Summarizes content using OpenAI's chat model
- Saves output to a user-friendly Markdown file
This contribution supports browser-based content summarization and expands the repo’s AI toolset for web interaction tasks.
2025-07-18 15:04:38 -05:00
Edward Donner
2f7a639afa
Linked to guides
2025-05-11 10:05:12 -04:00
Edward Donner
fb636df434
Added link to OpenAI Agents SDK and MCP implementation to final lab
2025-04-28 09:19:31 -04:00
Edward Donner
344219c9f3
Updates and added day1 with ollama
2025-04-05 10:01:00 -04:00
Edward Donner
e13549f846
Fixed problem with a missing extension on a community contribution
2025-02-15 21:17:03 -05:00
Edward Donner
6e946578eb
Fixed a typo
2025-02-15 17:48:52 -05:00
Edward Donner
6e27b37e45
Wording tweaks
2025-02-15 12:12:43 -05:00
Edward Donner
b5f0cd7905
Wording fixes
2025-02-15 11:08:15 -05:00
Edward Donner
ec4ada6456
Additional resources and tips
2025-02-15 08:31:06 -05:00
Edward Donner
e334b841ca
Improvements to explanations and minor edits
2025-01-05 12:51:20 -05:00
Edward Donner
90f3fe774a
Linux setup instructions, VSCode alternative, improved .env loading
2024-12-27 23:25:47 +00:00
Edward Donner
b6c06fd010
More troubleshooting tips added
2024-12-27 17:30:17 +00:00
Edward Donner
38c2317c0e
Minor refinements
2024-12-10 22:18:25 -05:00
Edward Donner
7f8697654d
Package updates, more Ollama, fixes
2024-12-08 22:57:40 -05:00
Edward Donner
58d1d488fb
Added diagnostics info
2024-11-19 18:41:54 -05:00
Edward Donner
4d7e21efa3
Minor diagnostics updates
2024-11-19 18:32:06 -05:00
Edward Donner
dab7973a80
Added diagnostics reports to debug any issues
2024-11-19 18:17:09 -05:00
Edward Donner
f4206653c3
Updated explanations and tips
2024-11-18 16:57:26 -05:00
Edward Donner
21c7a8155c
Refreshed notebooks, particularly with new Week 1
2024-11-13 15:46:22 +00:00
Edward Donner
421f4c69a4
Further troubleshooting instructions, also a minor compatibility fix
2024-11-03 11:42:01 -05:00
Edward Donner
05b078e6e1
Troubleshooting and wording improvements
2024-10-28 09:59:32 -04:00
Edward Donner
2fed25d515
Merge branch 'main' of github.com:ed-donner/llm_engineering
2024-10-28 09:51:54 -04:00
Edward Donner
513c95a98a
More instructions and comments
2024-10-28 09:51:45 -04:00
Kevin Kelly
ac922f3f6d
Jupyer -> Jupyter
2024-10-22 13:32:08 -05:00
Edward Donner
8ac9ccdf91
Added note about CloudFront protections - thank you Andy J!
2024-10-21 08:48:00 -04:00
Edward Donner
0a64893188
More troubleshooting and setup tips, and some improvements to flagship Week 8 project
2024-10-20 15:24:40 -04:00
Edward Donner
ca67bf1af9
More comments, more business applications, and links to pkl files
2024-10-05 10:30:21 -04:00
Edward Donner
a775465e3d
Organized community contributions and reset originals
2024-10-04 20:56:05 -04:00
Ed Donner
36d3f019ea
Merge branch 'main' into SD_enhancements
2024-10-04 20:33:27 -04:00
Edward Donner
196b6aea82
Week 8 updates
2024-09-29 22:16:56 -04:00
Simon Dufty
bdd3ef77e0
enhanced structure and comments for week 1 and added a Spanish version
2024-09-29 13:23:36 +10:00
Edward Donner
2f997952fc
Updated README and Week 8 coming together
2024-09-26 10:04:55 -04:00
Edward Donner
623955c25b
Updated README and projects with details of APIs and costs, and common setup troubleshooting
2024-09-22 08:50:46 -04:00
Edward Donner
21afbd6c73
Tidying up
2024-09-16 10:54:20 -04:00
Edward Donner
b83998ce00
Initial commit with weeks 1-4
2024-09-07 13:24:54 -04:00
