Adding transformation from Google Docs

process/google-docs-reader/README.md

@@ -0,0 +1,12 @@
+# Transform from Google Docs
+
+This script will read a **published** google docs spreadsheet, configured according to a standard template, and will parse out selected sheets.
+
+It caches entities as it reads across sheets, so if a company is discovered across multiple sheets (for example) it will assign the same identifier each time. 
+
+## Usage
+
+```
+python transform-from-gdocs.py <SPREADSHEET URL>
+```
+

process/google-docs-reader/transform-from-gdocs.py

@@ -0,0 +1,33 @@
+import sys, os
+import re 
+import requests
+import json
+sys.path.insert(1, os.path.join(sys.path[0], '../../modules/'))
+from taglifter import TagLifter
+from rdflib import Graph
+
+
+sheets_to_parse = ['Sources','Companies and Groups','Projects, sites & companies','Payments','Production']
+
+
+tl = TagLifter(ontology = "../../ontology/resource-projects-ontology.rdf",base="http://resourceprojects.org/",source_meta={})
+
+gdoc = str(sys.argv[1])
+result = re.search("([-\w]{25,})", gdoc)
+key = result.group(0)
+
+sheetlist = requests.get('https://spreadsheets.google.com/feeds/worksheets/'+key+'/public/full?alt=json')
+
+sheetjson = json.loads(sheetlist.text)
+
+for entry in sheetjson['feed']['entry']:
+    if entry['title']['$t'] in sheets_to_parse:
+        for link in entry['link']:
+            if link['type'] == "text/csv":
+                print(link['href'])
+                print("Loading " + entry['title']['$t'])
+                tl.graph = Graph()
+                tl.load_data(link['href'])
+                tl.build_graph()
+                tl.graph.serialize(format='turtle',destination="data/"+entry['title']['$t']+".ttl")
+