Converting the entire TMDB database's jsons to a single csv. Usage: ./tmdbdump_to_csv.py && ./tmdbdump_to_csv_merge.sh

tmdbdump_to_csv.py

#!/usr/bin/env python

# 1. Download TMDB's database with @galli-leo's script
#    https://gist.github.com/galli-leo/6398f9128ffc20af70c6c7eedfeb0a65
# 2. Run python3 tmdbdump_to_csv.py

import pandas as pd
import numpy as np
import json
import os

def jsonToDict(filename):
    f = open(filename)
    dic = json.loads(f.read())
    dic['tmdb_id'] = os.path.basename(filename).split('.')[0]
    f.close()
    return dic

files = os.listdir('TMDBDUMP')
files.sort(key=lambda x: int(x.split('.')[0]))

dics = []
for i,f in enumerate(files, 1):
    print("Dumping {} ({} of {})".format(f,i,len(files)))
    dics.append(jsonToDict('TMDBDUMP/'+f))

print("Creating dataset...")

df = pd.DataFrame(dics)

df['tmdb_id'] = pd.to_numeric(df['tmdb_id'])
df = df.set_index('tmdb_id')

print("Sorting...")
df = df.sort_index()

fname = f"tmdbdump.csv"
print(f"Saving as {fname} ...")
df.to_csv(fname)
print("Done!")