input = open(file, "r")
for line in input:
if ("<title>" in line):
title = re.sub(
r'^\s*<title>', '',
line) # Remove title tags. I'm sure there's some way to
title = re.sub(r'\s*</title>\s*', '',
title) # do this in one line.
recipeContent = recipeContent + line
if ("<url>" in line):
url = re.sub(
r'^\s*<url>', '',
line) # Remove url tags. I'm sure there's some way to
url = re.sub(r'\s*</url>\s*', '', url) # do this in one line.
##print(file + ': ' + url)
recipeContent = recipeContent + line
input.close()
recipeDataArray.append([title, url, recipeContent])
print('# starting to calculate embeddings: ' + time.strftime('%H:%M:%S'))
# Calculate and save embeddings
for r in recipeDataArray:
recipeEmbedding = obj.getFlairEmbedding(r[recipeField])
r.append(recipeEmbedding)
pickle.dump(recipeDataArray,
open(recipeDirectory + "recipeDataArray.p", "wb"))
print('# finished: ' + time.strftime('%H:%M:%S'))
