codeTries.txt

>>> for node in doc.getElementsByTagName("TOPICS"):
...   L = node.getElementsByTagName("D")
...   for node2 in L:
...     for node3 in node2.childNodes:
...       if node3.nodeType == Node.TEXT_NODE:
...         print node3.data
... 
cocoa


>>> for node in doc.getElementsByTagName("REUTERS"):
...   L = node.getElementsByTagName("TITLE")
...   for node2 in L:
...     title = ""
...     for node3 in node2.childNodes:
...       if node3.nodeType == Node.TEXT_NODE:
...         title += node3.data
...   print title
... 
BAHIA COCOA REVIEW
STANDARD OIL <SRD> TO FORM FINANCIAL UNIT
TEXAS COMMERCE BANCSHARES <TCB> FILES PLAN
TALKING POINT/BANKAMERICA <BAC> EQUITY OFFER


>>> for node in doc.getElementsByTagName("REUTERS"):
...     topic = node.getAttribute("TOPICS")
...     print topic
... 
YES
NO
NO
NO


>>> for node in doc.getElementsByTagName("REUTERS"):
...   L = node.getElementsByTagName("DATE")
...   for node2 in L:
...     if node2.nodeType == Node.TEXT_NODE:
...     for node3 in node2.childNodes:
...       if node3.nodeType == Node.TEXT_NODE:
...         print node3.data
... 
26-FEB-1987 15:01:01.79
26-FEB-1987 15:02:20.00
26-FEB-1987 15:03:27.51
26-FEB-1987 15:07:13.72


>>> for node in doc.getElementsByTagName("REUTERS"):
...   lewisSplit = node.getAttribute("LEWISSPLIT")
...   print lewisSplit
...   cgiSplit = node.getAttribute("CGISPLIT")
...   print cgiSplit
... 
TRAIN
TRAINING-SET
TRAIN
TRAINING-SET
TRAIN
TRAINING-SET
TRAIN
TRAINING-SET


>>> for node in doc.getElementsByTagName("REUTERS"):
...   topics = node.getAttribute("TOPICS")
...   print topics
...   lewisSplit = node.getAttribute("LEWISSPLIT")
...   print lewisSplit
...   cgiSplit = node.getAttribute("CGISPLIT")
...   print cgiSplit
...   oldId = node.getAttribute("OLDID")
...   print oldId
...   newId = node.getAttribute("NEWID")
...   print newId
... 
YES
TRAIN
TRAINING-SET
5544
1
NO
TRAIN
TRAINING-SET
5545
2
NO
TRAIN
TRAINING-SET
5546
3
NO
TRAIN
TRAINING-SET
5547
4
YES
TRAIN
TRAINING-SET
5548
5
YES
TRAIN
TRAINING-SET
5549
6