initial import of material for public archive into git

We're creating a fresh archive because the history for our old chapter includes
API keys, data files, and other material we can't share.

code/data_collection/02_get_cited_by.py

@@ -0,0 +1,43 @@
+from request_functions import *
+import argparse
+import json
+import subprocess
+from os import remove
+
+def main():
+
+    parser = argparse.ArgumentParser(description='Output JSON of all articles which cite the articles passed in')
+    parser.add_argument('-i', help='JSON file which includes eids and citedby-count')
+    parser.add_argument('-o', help='Where to append JSON results')
+    args = parser.parse_args()
+
+    with open(args.i, 'r') as f:
+        # Make a dictionary of eid:citation count for each line in the file
+        eids = {}
+        for line in f:
+            l = json.loads(line)
+            eids[l['eid']] = l['citedby-count']
+
+    # If the script gets interrupted, we need to start where we left off
+    try:
+        # Open the output file, and grab all of the eids which are already completed
+        with open(args.o, 'r') as f:
+            completed_eids = [json.loads(l)['parent_eid'] for l in f]
+        # Remove those which came from the last id (since we may have missed some)
+        if len(completed_eids) > 0:
+            last_eid = completed_eids.pop()
+            # Remove all of the lines which came from the last eid
+            subprocess.call(['sed', '-i.bak', '/parent_eid": "{}/d'.format(last_eid), args.o])
+            # Hopefully everything has worked out, because here we blow away the backup
+            remove('{}.bak'.format(args.o))
+    except IOError:
+        # If the file doesn't exist, then there aren't any completed eids
+        completed_eids = []
+
+    with open(args.o, 'a') as out_file:
+        for eid, citation_count in eids.items():
+            if citation_count != '0' and eid not in completed_eids:
+                get_cited_by(eid, out_file)
+
+if __name__ == '__main__':
+    main()