add import script

csv2mongodb.py

@@ -0,0 +1,58 @@
+import csv
+import re
+from datetime import datetime
+
+from pymongo import Connection
+connection = Connection()
+
+db = connection.cablegates
+cables = db.cables
+
+from pymongo import ASCENDING
+
+#http://cryptome.org/z/z.7z 
+csv_filename = 'data/cables.csv'
+
+#http://88.80.16.63/torrent/cablegate/cablegate-201108300212.7z.torrent
+html_cables = 'data/cables'
+
+#incomplete/same info as csv
+#http://file.wikileaks.org/torrent/cable_db_full.7z.torrent
+
+if __name__ == "__main__":
+    cables.create_index([('refid', ASCENDING),])
+
+
+    csv.field_size_limit(1024*1024*2)
+    reader = csv.reader(open(csv_filename, 'rb'), delimiter=',', quotechar='"', escapechar="\\")
+
+    n = 0
+    for row in reader:
+        cable = {}
+        keys = ['id',
+                'created', 'refid', 'origin', 'classification', 'destination', 'header', 'content']
+
+        #skip id, integer id of csv dump
+        for i in range(0, len(keys)):
+            cable[keys[i]] = row[i].strip()
+
+        cable['created'] = datetime.strptime(cable['created'], '%m/%d/%Y %H:%M')
+        html = '%s/cable/%s/%s.html' % (html_cables, 
+               cable['created'].strftim('%Y/%m'), cable['refid'])
+        with open(html) as f:
+            data = f.read()    
+            cable['released'] = re.compile("<a href='/reldate/.*?'>(.*?)</a>").findall(data)[-1]
+
+        data = cable['content']
+        if 'SUBJECT: ' in data:
+            cable['subject'] = re.compile('SUBJECT: (.*?)( \n \n|$)',
+                               re.DOTALL).findall(data)[0][0].replace('\n', '').strip()
+            print cable['subject']
+        if 'TAGS: ' in data:
+            cable['tags'] = re.compile('TAGS: (.*?)( \n|$)',
+                            re.DOTALL).findall(data)[0][0].replace('\n', '').strip().split(', ')
+
+        print n, data['refid']
+        cables.save(data)
+        n += 1
+