#!/usr/bin/python3
#
# Program to dump a MediaProcessor DB into a folder of html files
#
# This will create an index.html file that has links to all files
# produced by this program. Each file is named by the IPFS hash
# for the media content. It contains all of the metadata and as a
# hidden set of name/value pairs with a few visible lines for use
# in a web browser.
#
import datetime
import sqlite3
import time
import sys
import os
def usage():
cmd = sys.argv[0]
str = "\nCreates a file for each row of the target SQLite database.\n"
str += "Usage: " + cmd + " <-d sqlite DB file> <-f folder> [-s since]\n\n"
print(str)
exit(0)
HTML1 = "\n\t\n\t\t\n\t\t\t"
HTML2 = "\n\t\t\n\t\t\n"
HTML3 = "\n\n\n"
#############################################################################
# #
# main #
# #
#############################################################################
argc = len(sys.argv)
cols = []
conn = sql = row = url = since = None
try:
# Parse command line
if argc > 4:
# Required parameter: SQLite database file to check pins against
if sys.argv[1] == "-d":
dbFile = sys.argv[2]
conn = sqlite3.connect(dbFile) # Failure to open is exception
conn.row_factory = sqlite3.Row # Result format to dictionary
else: usage()
# Required parameter: folder where files will be written
if sys.argv[3] == "-f":
folder = sys.argv[4]
if not os.path.exists(folder):
os.mkdir(folder)
else: usage()
# Optional parameter: since date
if argc == 7:
if sys.argv[5] == "-s":
try:
since = sys.argv[6]
datetime.datetime.strptime(since, '%Y-%m-%d')
except Exception:
print("Incorrect date format, must be YYYY-MM-DD")
exit(0)
else: usage()
else: usage()
# Make an index.html file with links to all files generated
with open(folder + "/index.html", 'w') as idx:
idx.write(HTML1 + "IPFS Hash Index" + HTML2 + "\n")
sql = "SELECT vhash FROM IPFS_HASH_INDEX ORDER BY grupe, sqlts"
rows = (conn.cursor().execute(sql)).fetchall()
for row in range(0, len(rows)):
vhash = rows[row]['vhash']
if vhash and len(vhash) == 46:
idx.write(f"{vhash} ")
if (row + 1) % 3 == 0: idx.write('\n')
idx.write(HTML3)
# Create the files, with contents being all metadata fields & values.
# Display a few items at top of file and leave most hidden.
sql = "SELECT * FROM IPFS_HASH_INDEX "
rows = conn.cursor().execute(sql + "limit 1;")
for col in rows.description: # First get column names
cols.append(col[0])
if since: sql += f"WHERE sqlts >= '{since}' "
sql += "ORDER BY grupe, sqlts"
rows = (conn.cursor().execute(sql)).fetchall() # Now get the column values
fiveSpaces = " "
for row in rows:
vhash = row['vhash']
if not vhash or len(vhash) < 46: continue
file = folder + '/' + row['vhash'] + ".html"
with open(file, 'w') as f:
f.write(HTML1 + row['title'] + HTML2)
ipfs = f"http://127.0.0.1:8080/ipfs/{row['vhash']}"
url = f"{row['webpage_url']}"
f.write(f"\t\t\t\n")
f.write(f"\t\t\tTitle:{fiveSpaces} {row['title']}
\n")
f.write(f"\t\t\tSource:{fiveSpaces} {url}
\n")
f.write(f"\t\t\tDescription:\n")
f.write(f"\t\t\t{row['description']}
\n")
# Remainder of columns will only be visible with "show page source"
f.write(f"\n")
for col in cols:
f.write(f"{col} = {row[col]}\n")
f.write(HTML3)
except sqlite3.Error as e:
print("Database error during query: %s\nSQL=%s\n\n" % (e, sql))
except sqlite3.OperationalError:
print("ERROR!: Query Failure")
except Exception as e:
print("Exception: %s\n\n" % e)
exit(0)