<pre><code>#CODE:
#!/usr/bin/python
import subprocess
import json
import os
subprocess.call('cd /home/adrian/from_hdfs; for f in *; do (cat "${f}"; echo) >> notfinal.txt; done', shell=True) =====> I am using this to generate "data.txt" from your example
directory = "/home/adrian/from_hdfs/"
parsed = {}
with open('/home/adrian/from_hdfs/notfinal.txt') as json_file:
parsed = json.load(json_file)
#open output file
with open("finalfile.txt", "a") as outfile:
#loop through src directory
for filename in os.listdir(directory):
if filename in parsed:
continue # skip file if already read
file_abs = os.path.join(directory, filename)
#print("Reading file: "+file_abs)
with open(file_abs, "r") as src_file:
myfile.write(src_file.read()) #append data from src to dest
parsed[filename] = 1
with open('result.json', 'w') as fp:
json.dump(parsed, fp)
Traceback (most recent call last):
File "./script.py", line 14, in <module>
parsed = json.load(json_file)
File "/usr/lib/python2.7/json/__init__.py", line 291, in load
**kw)
File "/usr/lib/python2.7/json/__init__.py", line 339, in loads
return _default_decoder.decode(s)
File "/usr/lib/python2.7/json/decoder.py", line 364, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/usr/lib/python2.7/json/decoder.py", line 382, in raw_decode
raise ValueError("No JSON object could be decoded")
ValueError: No JSON object could be decoded
</code></pre>