Created
November 3, 2015 19:02
-
-
Save salayhin/7aaf34fa4fc29e9d8ed1 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Note - this code must run in Python 2.x and you must download | |
# http://www.pythonlearn.com/code/BeautifulSoup.py | |
# Into the same folder as this program | |
import urllib | |
from BeautifulSoup import * | |
position = raw_input('Enter Position - ') | |
count = raw_input('Enter Count - ') | |
url_first = raw_input('Enter - ') | |
url = '' | |
# Retrieve all of the anchor tags | |
s = [] | |
for x in range(0, int(count)): | |
if x == 0: | |
html = urllib.urlopen(url_first).read() | |
soup = BeautifulSoup(html) | |
tags = soup('a') | |
tag = tags[int(position) - 1] | |
url = tag.get('href', None) | |
s.append(tag.contents[0]) | |
elif x > 0: | |
html = urllib.urlopen(url).read() | |
soup = BeautifulSoup(html) | |
tags = soup('a') | |
tag = tags[int(position) - 1] | |
url = tag.get('href', None) | |
s.append(tag.contents[0]) | |
#for tag in tags: | |
# print tag.get('href', None) | |
print s |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment