script to parse nzpug mail list


In [78]:
import requests

In [79]:
import xmltodict

import json
import random
import pandas

In [80]:
nzpreq = requests.get('https://groups.google.com/forum/feed/nzpug/topics/rss.xml?num=10')

In [81]:
convxml = xmltodict.parse(nzpreq.text)

In [82]:
totlen = len(convxml['rss']['channel']['item'])

In [83]:
ranint = random.randint(0, totlen)

In [ ]:


In [ ]:


In [ ]:


In [84]:
nzpubtit = convxml['rss']['channel']['item'][ranint]['title']

In [85]:
nzpund = nzpubtit.replace(' ', '_')

In [ ]:


In [88]:
pubd = convxml['rss']['channel']['item'][ranint]['pubDate']

In [ ]:


In [89]:
pandat = pandas.to_datetime(pubd)

In [90]:
str(pandat.date())


Out[90]:
'2015-09-02'

In [91]:
savti = open('/home/wcmckee/nzpug/posts/' + nzpund + '.meta', 'w')

In [ ]:


In [92]:
savti.write(nzpubtit + '\n' + nzpund + '\n' + str(pandat.date()) + ' ' + str(pandat.time()))


Out[92]:
119

In [97]:
autho = convxml['rss']['channel']['item'][ranint]['author']

In [98]:
conlink = convxml['rss']['channel']['item'][ranint]['link']

In [99]:
condes = convxml['rss']['channel']['item'][ranint]['description']

In [100]:
savti.close()

In [101]:
savrst = open('/home/wcmckee/nzpug/posts/' + nzpund + '.rst', 'w')

In [102]:
savrst.write(nzpubtit + '\n' + autho + '\n' + condes)


Out[102]:
356

In [103]:
savrst.close()

In [ ]:


In [ ]:


In [68]:
str(pandat.time())


Out[68]:
'00:22:43'

In [ ]:


In [ ]:


In [ ]:


In [ ]:


In [ ]: