From 5b14013246e56acb316ceaff395a487495a2bfa2 Mon Sep 17 00:00:00 2001
From: K V Ragul <cb.en.u4cse16237@cb.students.amrita.edu>
Date: Wed, 6 Mar 2019 13:06:25 +0530
Subject: [PATCH] Periodical 2
---
cb.en.u4cse16237_p2_q2.py | 38 ++++++++++++++++++++++++++++++++++++++
1 file changed, 38 insertions(+)
create mode 100644 cb.en.u4cse16237_p2_q2.py
diff --git a/cb.en.u4cse16237_p2_q2.py b/cb.en.u4cse16237_p2_q2.py
new file mode 100644
index 0000000..315de18
--- /dev/null
+++ b/cb.en.u4cse16237_p2_q2.py
@@ -0,0 +1,38 @@
+import requests
+from urllib.request import urlopen
+from bs4 import BeautifulSoup
+
+page = requests.get("https://news.google.com/?hl=en-IN&gl=IN&ceid=IN:en")
+page1 = requests.get("https://in.news.yahoo.com/")
+bus = requests.get("https://news.google.com/topics/CAAqJggKIiBDQkFTRWdvSUwyMHZNRGx6TVdZU0FtVnVHZ0pKVGlnQVAB?hl=en-IN&gl=IN&ceid=IN%3Aen")
+page2 = requests.get("https://www.rediff.com/headline.html")
+
+
+
+list1 = []
+list2 = []
+list3 = []
+
+
+
+soup = BeautifulSoup(page.content, 'html.parser')
+soup1 = BeautifulSoup(page1.content, 'html.parser')
+soup2 = BeautifulSoup(page2.content, 'html.parser')
+
+for line in soup.select('a'):
+ if len(line) > 25:
+ list1.append(line.get_text())
+
+for line1 in soup1.select('a'):
+ if len(line1) > 25:
+ list2.append(line1.get_text())
+
+for line2 in soup2.select('a'):
+ if len(line2) > 25:
+ list3.append(line2.get_text())
+
+print(list1[:10])
+print(list2[:10])
+print(list3[:10])
+
+
--
GitLab