Scraping all the links in a web page.

Ishan7390 · Nov 10, 2019 · 90f45e9 · 90f45e9
1 parent f425068
commit 90f45e9
Showing 1 changed file with 23 additions and 0 deletions.
diff --git a/links_all.py b/links_all.py
@@ -0,0 +1,23 @@
+import requests
+import bs4
+link_list=[]
+res = requests.get('https://www.apple.com/')
+soup = bs4.BeautifulSoup(res.text, 'lxml')
+
+for link in soup.find_all('a', href=True):
+	'''link_list.append(link)
+	# if link[0]=='#':
+ 	# 	link_list.remove(link)
+ 	if link[0]=='/':
+		link_list.remove(link)
+
+ link_list
+'''
+	# if link['href']!="#":
+	# 	print(link["href"])
+	if link['href'][0]=='#':
+		pass
+	elif link['href'][0]=='/':
+		pass
+	else:
+		print(link['href'])