Skip to content

Lab solution to lab-web-scraping.ipynb #359

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Lab solution to lab-web-scraping.ipynb #359

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
110 changes: 105 additions & 5 deletions lab-web-scraping.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,14 +110,114 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"id": "40359eee-9cd7-4884-bfa4-83344c222305",
"metadata": {
"id": "40359eee-9cd7-4884-bfa4-83344c222305"
},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\LAP-MPC\\AppData\\Local\\Temp\\ipykernel_10456\\493026631.py:42: DeprecationWarning: The 'text' argument to find()-type methods is deprecated. Use 'string' instead.\n",
" upc = book_soup.find(text='UPC').find_next('td').text\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" UPC Title \\\n",
"0 ce6396b0f23f6ecc Set Me Free \n",
"1 6258a1f6a6dcfe50 The Four Agreements: A Practical Guide to Pers... \n",
"2 6be3beb0793a53e7 Sophie's World \n",
"3 657fe5ead67a7767 Untitled Collection: Sabbath Poems 2014 \n",
"4 51653ef291ab7ddc This One Summer \n",
"\n",
" Price (£) Rating Genre Availability \\\n",
"0 17.46 5 Young Adult In stock (19 available) \n",
"1 17.66 5 Spirituality In stock (18 available) \n",
"2 15.94 5 Philosophy In stock (18 available) \n",
"3 14.27 4 Poetry In stock (16 available) \n",
"4 19.49 4 Sequential Art In stock (16 available) \n",
"\n",
" Description \n",
"0 Aaron Ledbetter’s future had been planned ou... \n",
"1 In The Four Agreements, don Miguel Ruiz reveal... \n",
"2 A page-turning novel that is also an explorati... \n",
"3 More than thirty-five years ago, when the weat... \n",
"4 Every summer, Rose goes with her mom and dad t... \n"
]
}
],
"source": [
"# Your solution goes here"
"import requests\n",
"from bs4 import BeautifulSoup\n",
"import pandas as pd\n",
"\n",
"def get_rating(rating_class):\n",
" \"\"\"Convert star rating class names to numerical ratings.\"\"\"\n",
" ratings_map = {'One': 1, 'Two': 2, 'Three': 3, 'Four': 4, 'Five': 5}\n",
" return ratings_map.get(rating_class, 0)\n",
"\n",
"def scrape_books(min_rating=4.0, max_price=20.0):\n",
" base_url = 'http://books.toscrape.com/catalogue/page-{}.html'\n",
" books_data = []\n",
"\n",
" page = 1\n",
" while True:\n",
" response = requests.get(base_url.format(page))\n",
" soup = BeautifulSoup(response.text, 'html.parser')\n",
" \n",
" # Check if there are books on the current page\n",
" books = soup.select('article.product_pod')\n",
" if not books:\n",
" break\n",
"\n",
" for book in books:\n",
" rating_class = book.p['class'][1]\n",
" rating = get_rating(rating_class)\n",
" title = book.h3.a['title']\n",
" \n",
" # Properly handle the price by removing non-numeric prefixes\n",
" price_text = book.find('p', class_='price_color').text\n",
" price_cleaned = ''.join(filter(lambda x: x.isdigit() or x=='.', price_text))\n",
" price = float(price_cleaned)\n",
"\n",
" if rating >= min_rating and price <= max_price:\n",
" # Extract the link and fetch additional book details\n",
" relative_link = book.h3.a['href'].replace('../../../', '')\n",
" book_url = f\"http://books.toscrape.com/catalogue/{relative_link}\"\n",
" book_response = requests.get(book_url)\n",
" book_soup = BeautifulSoup(book_response.text, 'html.parser')\n",
" \n",
" # Extract additional book details\n",
" upc = book_soup.find(text='UPC').find_next('td').text\n",
" genre = book_soup.find('ul', class_='breadcrumb').findAll('a')[2].text\n",
" availability = book_soup.find('p', class_='instock availability').text.strip()\n",
" description_tag = book_soup.find('meta', attrs={'name': 'description'})\n",
" description = description_tag['content'].strip() if description_tag else 'N/A'\n",
"\n",
" books_data.append({\n",
" 'UPC': upc,\n",
" 'Title': title,\n",
" 'Price (£)': price,\n",
" 'Rating': rating,\n",
" 'Genre': genre,\n",
" 'Availability': availability,\n",
" 'Description': description\n",
" })\n",
"\n",
" page += 1\n",
"\n",
" # Create a DataFrame with the book data\n",
" books_df = pd.DataFrame(books_data)\n",
" return books_df\n",
"\n",
"# Execute the function\n",
"books_df_result = scrape_books(min_rating=4.0, max_price=20.0)\n",
"print(books_df_result.head())"
]
}
],
Expand All @@ -126,7 +226,7 @@
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "base",
"language": "python",
"name": "python3"
},
Expand All @@ -140,7 +240,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
"version": "3.13.5"
}
},
"nbformat": 4,
Expand Down