f44947c8a0
Decided to knock up a quick proof of concept for fetching and parsing tournament results from a website. Specifically uses: - Pythons Beautiful Soup library - P5s results pages - replace playername with the desired p5s username (eg. taypaur) Of note; no tournament ids are displayed on any of the sites, so for this to work we may need to add a field like 'p5sid'
34 lines
898 B
Python
34 lines
898 B
Python
import urllib2, re
|
|
import pprint
|
|
from BeautifulSoup import BeautifulSoup
|
|
|
|
|
|
playername = ''
|
|
|
|
if playername == '':
|
|
print "You need to manually enter the playername"
|
|
exit(0)
|
|
|
|
page = urllib2.urlopen("http://www.pocketfives.com/poker-scores/%s/" %playername)
|
|
soup = BeautifulSoup(page)
|
|
|
|
results = []
|
|
|
|
for table in soup.findAll('table'):
|
|
# print "Found %s" % table
|
|
for row in table.findAll('tr'):
|
|
tmp = []
|
|
for col in row.findAll('td'):
|
|
tmp = tmp + [col.string]
|
|
#print col.string
|
|
if len(tmp) > 3 and tmp[2] <> None:
|
|
results = results + [tmp]
|
|
|
|
cols = ['TOURNAMENT', 'SITE', 'DATE', 'PRIZEPOOL', 'BUY-IN', 'PLACE', 'WON']
|
|
|
|
pp = pprint.PrettyPrinter(indent=4)
|
|
|
|
for result in results:
|
|
print "Site: %s Date: %s\tPrizepool: %s\tBuyin: %s\tPosition: %s\tWon: %s" %(result[2], result[3], result[4], result[5], result[6], result[7])
|
|
|