import urllib from bs4 import BeautifulSoup import re
sumt = 0
html = urllib.urlopen('http://python-data.dr-chuck.net/comments_338391.html').read()
soup = BeautifulSoup(html)
tags = soup('span')
for lne in tags: lne = str(lne) data = re.findall('[0-9]+',lne) data[0] = int(data[0]) sumt = sumt + data[0]
print sumt
Error:
IOError: [Errno socket error] [Errno 11004] getaddrinfo failed
Please note, that urllib.urlopen is deprecated; you should use urllib2.urlopen.
Anyhow, for me both versions work fine.
import urllib2
import re
if __name__ == '__main__':
url = 'http://python-data.dr-chuck.net/comments_338391.html'
comments = {}
pattern = re.compile('<tr><td>(?P<name>.+?)</td>.+?class="comments">(?P<count>\d+)</span>.+?')
for line in urllib2.urlopen(url).read().split('\n'):
m = pattern.match(line)
if m:
comments[m.group('name')] = int(m.group('count'))
print(comments)
Yields:
{'Caidan': 28, 'Haylie': 59, 'Fikret': 43, 'Tabbitha': 54, 'Rybecca': 70, 'Pearl': 45, 'Kiri': 72, 'Storm': 66, 'Kelum': 55, 'Elisau': 30, 'Lexi': 70, 'Cobain': 2, 'Theodore': 36, 'Ammer': 26, 'Carris': 87, 'Fion': 10, 'Derick': 28, 'Shalamar': 98, 'Adil': 93, 'Wasif': 54, 'Yasin': 78, 'Mhyren': 92, 'Kodi': 75, 'Nikela': 98, 'Lorena': 76, 'Seth': 68, 'Lillia': 91, 'Nitya': 26, 'Tigan': 73, 'Jaii': 11, 'Kamran': 74, 'Arianna': 12, 'Mercedes': 92, 'Gregory': 40, 'Umaima': 83, 'Rhylee': 26, 'Kaia': 91, 'Hamid': 33, 'Lucien': 5, 'Zacharias': 92, 'Abir': 35, 'Teejay': 51, 'Muir': 43, 'Hena': 84, 'Alanas': 16, 'Lybi': 91, 'Atiya': 87, 'Kayleb': 7, 'Fletcher': 87, 'Lisandro': 78}
i.e.: works for me.
