From e3ac12ff9b047a8582b7f1a189a14a73a3ea1ed1 Mon Sep 17 00:00:00 2001
From: yann <yann@needsome.coffee>
Date: Wed, 13 Nov 2024 15:46:48 +0100
Subject: [PATCH] get category_list from home and get product url from a
 category (if one page)

---
 phase2/main.py | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/phase2/main.py b/phase2/main.py
index e69de29..d5a90da 100644
--- a/phase2/main.py
+++ b/phase2/main.py
@@ -0,0 +1,36 @@
+import requests
+from bs4 import BeautifulSoup
+
+url = "https://books.toscrape.com/"
+r = requests.get(url)
+html = r.content
+soup = BeautifulSoup(html, 'html.parser')
+
+
+category = "travel"
+
+catego_info = []
+catego_dict = {}
+# get category and URL from side div and put them as a list [catego, url] in a list
+
+def get_category_list(soup):
+    catego_info = []
+    catego_dict = {}
+    for li in soup.find("div", class_="side_categories").find_all("li"):
+        catego_info.append([li.a.get_text(strip = True).lower(), url + li.a.get('href')])
+        catego_dict[li.a.get_text(strip = True).lower()] = url + li.a.get('href')
+    return catego_dict
+
+
+page_url = get_category_list(soup)['travel']
+soup2 = BeautifulSoup(requests.get(page_url).content, "html.parser")
+
+def get_product_list(soup):
+    list = []
+    for i in soup.find_all("article"):
+        relative_url = i.h3.a.get('href')
+        product_url = url + relative_url.split('../')[-1]
+        list.append(product_url)
+    return(list)
+
+print(len(get_product_list(soup2)))