datasetsss

1 files changed, 10 insertions, 1 deletions

diff --git a/scraper/s2-citation-report.py b/scraper/s2-citation-report.py
index 96400d45..fc52cc35 100644
--- a/scraper/s2-citation-report.py
+++ b/scraper/s2-citation-report.py
@@ -5,9 +5,12 @@ import simplejson as json
 import math
 import operator
 import click
+import subprocess
 #import builder
 from util import *
 
+DIR_PUBLIC_CITATIONS = "../site/datasets/citations"
+
 @click.command()
 def s2_citation_report():
   addresses = AddressBook()
@@ -30,6 +33,12 @@ def s2_citation_report():
   print("citations: {}".format(paper_count))
   print("geocoded: {} ({}%)".format(geocode_count, percent(geocode_count, paper_count)))
 
+  sts = subprocess.call([
+    "s3cmd", "sync",
+    DIR_PUBLIC_CITATIONS + '/',
+    "s3://megapixels/v1/citations/",
+  ])
+
 def write_papers_report(fn, title, papers, key, reverse=False):
   sorted_papers = []
   for paper in sorted(papers, key=lambda x: x[key], reverse=reverse):
@@ -262,7 +271,7 @@ def process_paper(row, addresses, success):
     f.write('<script src="../map.js"></script>')
     f.write("</html>")
   # template = env.get_template('paper.html')
-  with open('reports/citations/{}.json'.format(paper.paper_id), 'w') as f:
+  with open('{}/{}.json'.format(DIR_PUBLIC_CITATIONS, paper.paper_id), 'w') as f:
     json.dump({
       'id': paper.paper_id,
       'paper': res,