Last active
March 16, 2018 21:54
-
-
Save BTBTravis/9a3dc3a2da191e6cd5434eb1ce3ea810 to your computer and use it in GitHub Desktop.
Python Script to scrape images files out of data dump including with img src base64 encoded images
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/python | |
import re | |
# from base64 import decodestring | |
import base64 | |
# import base64 | |
f = open("dump.txt","r") | |
str = f.read() | |
# str = 'lalala <img src="data:image/png;base64,iVBORw0KGg"> lalala <img src="data:image/gif;base64,iVBORw0KGg">' | |
# str = '<img src="data:image/gif;base64,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"> ' | |
# <img src=\"data:image/png;base64 | |
# p = re.compile(r'src=\"data:image/([^;]+);base64,([^>]+)') | |
p = re.compile(r'src=\\"data:image\/([^;]+);base64,([^"]+)') | |
result = p.findall(str) | |
# m = re.search('scr="([^"]+)', str) | |
print(len(result)) | |
# m.group(0) | |
# print(result) | |
def pad(data): | |
missing_padding = len(data) % 4 | |
if missing_padding != 0: | |
data += b'='* (4 - missing_padding) | |
return data | |
# return base64.decodestring(data) | |
for k,v in enumerate(result): | |
# print(k) | |
# print(v) | |
t = v[0] | |
s = v[1][:-1] | |
s = s.replace('\r\n', '') | |
p = pad(s) | |
# print({ | |
# 't': t, | |
# 's': s, | |
# 'pad': p | |
# }) | |
fh = open("dump_" + `k` + "." + t, "wb") | |
fh.write(p.decode('base64')) | |
# SELECT ptc.`pm_task_comment` FROM `pm_tasks` pt | |
# LEFT JOIN `pm_tasks_comments` ptc ON ptc.`issue_id` = pt.`pm_task_id` | |
# WHERE | |
# pt.`pm_tasks_client_id` = 179 | |
# AND ptc.`pm_task_comment` LIKE '%data%'; | |
# LIMIT 1; | |
input() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment