Periodical 2

cb.en.u4cse16237_p2_q2.py

+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])
+
+