Last active 1440820608

Get all bropages entries and output to folder

Steven Smith revised this gist 1393506968. Go to revision

1 file changed, 26 insertions

bropages.py(file created)

@@ -0,0 +1,26 @@
1 + import requests
2 + from os import mkdir, sep, listdir
3 + from BeautifulSoup import BeautifulSoup as Soup
4 + # Load page
5 + soup = Soup(requests.get("http://bropages.org/browse").text)
6 + # Get rows excluding header
7 + rows = soup.findAll('tr')[1:]
8 + cmds = []
9 + # iterate over rows, get commands, save list without duplicates
10 + for a in rows:
11 + out = a.find('td').text
12 + if not out in cmds:
13 + cmds.append(out)
14 + # make output directory if not already existing
15 + try:
16 + mkdir('bropages')
17 + except:
18 + pass
19 + # get output json, save to directory
20 + for cmd in cmds:
21 + try:
22 + with open('bropages{}{}.json'.format(sep, cmd), 'w') as f:
23 + f.write(requests.get('http://bropages.org/%s.json' % cmd).text)
24 + print "done " + cmd
25 + except UnicodeError: # stupid unicode
26 + continue
Newer Older