Carlos-Francisco Méndez-Cruz

Extract manually tagged GCs

......@@ -79,6 +79,11 @@ if __name__ == "__main__":
tag = m.group('tag')
content = m.group('content')
content = content.strip()
content = content.replace("&", "&")
content = content.replace("&lt;", "<")
content = content.replace("&gt;", ">")
content = content.replace("&quot;", "\"")
content = content.replace("&apos;", "\'")
print("\nSerie: {}\tSample: {}\tTag: {}\tContent: {}".format(serie, sample, tag, content.encode(encoding='utf-8', errors='replace')))
if tag in hashGcs[serie][sample]:
if content in hashGcs[serie][sample][tag]:
......