Created
February 6, 2014 07:07
-
-
Save hugovk/8839550 to your computer and use it in GitHub Desktop.
Hacky script used for renaming (most) of the Wikipedia/Wikimedia photos of members of congress into bioguide IDs for use by https://github.com/sunlightlabs/congress/
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import csv | |
import os | |
import re | |
import sys | |
def mvit(infile, outfile): | |
for suffix in [ | |
"_113th_Congress_2013", | |
"_113th_Congress", | |
"", | |
"_official_portrait", | |
"_portrait", | |
"_official", | |
"pic", | |
"%2C_official_113th_Congress_photo_portrait", | |
"_official_portrait_112th_Congress", | |
"_official_portrait%2C_2009", | |
"%2C_official_portrait%2C_112th_Congress", | |
"%2C_official_portrait%2C_113th_Congress", | |
"_2010", | |
"%2C_official_110th_Congress_photo", | |
"_official_photo", | |
"_113th", | |
"-Senate_Portrait", | |
"_Official_Photo_110th_Congress", | |
"2C_official_portrait%2C_112th_Congress_alternate", | |
"_official_portrait_2009_crop", | |
"--Official_113th_Congressional_Portrait--", | |
"_2013", | |
"_official_photo_2009_2", | |
"%2C_official_111th_Congress_photo_portrait", | |
]: | |
for suffix2 in [".jpg", "2.jpg", "_2.jpg"]: | |
infile2 = infile + suffix + suffix2 | |
mvexists(infile2, outfile) | |
infile2 = infile2.replace(" ", "_") | |
mvexists(infile2, outfile) | |
infile2 = infile2.translate(None, "_") | |
slashpos = infile2.index("/") | |
infile2 = infile2[0:slashpos+2] + infile2[slashpos+2:].lower() | |
mvexists(infile2, outfile) | |
def mvexists(infile, outfile): | |
if os.path.exists(infile): | |
cmd = "mv " + infile + " " + outfile | |
print cmd | |
os.rename(infile, outfile) | |
def main(): | |
filename = "legislators.csv" | |
ifile = open(filename, "rb") | |
# reader = csv.reader(ifile) | |
reader = csv.reader(x.replace('\0', '') for x in ifile) | |
rownum = 0 | |
for rownum,row in enumerate(reader): | |
# Save header row. | |
if rownum == 0: | |
header = row | |
for colnum, col in enumerate(row): | |
if re.match("title", col): | |
title = colnum | |
elif re.match("firstname", col): | |
firstname = colnum | |
elif re.match("middlename", col): | |
middlename = colnum | |
elif re.match("nickname", col): | |
nickname = colnum | |
elif re.match("lastname", col): | |
lastname = colnum | |
elif re.match("bioguide_id", col): | |
bioguide_id = colnum | |
else: | |
outfile = "done/" + row[bioguide_id] + ".jpg" | |
titletext = row[title] | |
if titletext == "Del": titletext = "Rep" | |
# First last | |
infile = titletext + "/" + row[firstname] + "_" + row[lastname] | |
mvit(infile, outfile) | |
infile = titletext + "/" + row[firstname] + row[lastname] | |
mvit(infile, outfile) | |
infile = titletext + "/" + row[firstname] + "*" + row[lastname] | |
mvit(infile, outfile) | |
# First middle last | |
infile = titletext + "/" + row[firstname] + "_" + row[middlename] + "_" + row[lastname] | |
mvit(infile, outfile) | |
# First initial last | |
if len(row[middlename]): | |
infile = titletext + "/" + row[firstname] + "_" + row[middlename][0] + "._" + row[lastname] | |
mvit(infile, outfile) | |
infile = titletext + "/" + row[firstname] + "_" + row[middlename][0] + "_" + row[lastname] | |
mvit(infile, outfile) | |
# Nickname last | |
if len(row[nickname]): | |
infile = titletext + "/" + row[nickname] + "_" + row[lastname] | |
mvit(infile, outfile) | |
ifile.close() | |
if __name__ =="__main__": | |
main() | |
# End of file |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment