diff --git a/week1/community-contributions/day5-disable-ssl.ipynb b/week1/community-contributions/day5-disable-ssl.ipynb new file mode 100644 index 0000000..90ac21c --- /dev/null +++ b/week1/community-contributions/day5-disable-ssl.ipynb @@ -0,0 +1,81 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "a98030af-fcd1-4d63-a36e-38ba053498fa", + "metadata": {}, + "source": [ + "# A Small Tweak to Week1-Day5\n", + "\n", + "If you have network restrictions (such as using a custom DNS provider, or firewall rules at work), you can disable SSL cert verification.\n", + "Once you do that and start executing your code, the output will be riddled with warnings. Thankfully, you can suppress those warnings,too.\n", + "\n", + "See the 2 lines added to the init method, below." + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "106dd65e-90af-4ca8-86b6-23a41840645b", + "metadata": {}, + "outputs": [], + "source": [ + "# A class to represent a Webpage\n", + "\n", + "# Some websites need you to use proper headers when fetching them:\n", + "headers = {\n", + " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36\"\n", + "}\n", + "\n", + "class Website:\n", + " \"\"\"\n", + " A utility class to represent a Website that we have scraped, now with links\n", + " \"\"\"\n", + "\n", + " def __init__(self, url):\n", + " self.url = url\n", + "\n", + " #\n", + " # If you must disable SSL cert validation, and also suppress all the warning that will come with it,\n", + " # add the 2 lines below. This comes in very handy if you have DNS/firewall restrictions; alas, use\n", + " # with caution, especially if deploying this in a non-dev environment.\n", + " requests.packages.urllib3.disable_warnings() \n", + " response = requests.get(url, headers=headers, verify=False) \n", + " # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n", + " \n", + " self.body = response.content\n", + " soup = BeautifulSoup(self.body, 'html.parser')\n", + " self.title = soup.title.string if soup.title else \"No title found\"\n", + " if soup.body:\n", + " for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", + " irrelevant.decompose()\n", + " self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", + " else:\n", + " self.text = \"\"\n", + " links = [link.get('href') for link in soup.find_all('a')]\n", + " self.links = [link for link in links if link]" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}