Created
June 4, 2018 05:26
-
-
Save Hrxn/130577a0989a689af8be5010380fc451 to your computer and use it in GitHub Desktop.
Python: Tumblr Stats Info
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
import argparse, time, re | |
import pytumblr | |
ap = argparse.ArgumentParser(description='tumblr.py: Process a text file of Tumblr Blog URLs.') | |
ap.add_argument('input_file', metavar='FILE', type=str, help='specifies the text file to process') | |
ap.add_argument('-v', '--values', action='store_true', help='prints only the user-ids in FILE') | |
args = ap.parse_args() | |
# Use your account credentials here for API access (OAuth) | |
client = pytumblr.TumblrRestClient( | |
'<consumer_key>', | |
'<consumer_secret>', | |
'<oauth_token>', | |
'<oauth_secret>', | |
) | |
outp_head = ( | |
'URL' ',' 'Title' ',' 'Tumblr ID' ',' 'Description' ',' 'Total Post Count' ',' | |
'Post Count (Photo)' ',' 'Post Count (Video)' ',' 'Post Count (The Rest)' ',' 'Last Updated' | |
) | |
rx_uid = re.compile(r"(?:(?:https?\:\/\/)(?P<id>.*\.[a-z]{2,16})(?:\/)?.*)") | |
def tumblr_id(s): | |
return re.sub(rx_uid, '\g<id>', s) | |
def clean_csv(s): | |
if isinstance(s, str): | |
return s.replace(',', '') | |
else: | |
return str(s).replace(',', '') | |
with open(args.input_file) as file: | |
lines = filter(None, (line.rstrip() for line in file)) | |
if args.values: | |
for v in lines: | |
uid = tumblr_id(v) | |
print(uid) | |
else: | |
print(outp_head) | |
for v in lines: | |
if not v[0] == '#': | |
uid = tumblr_id(v) | |
res = client.blog_info(uid) | |
res_p = client.posts(uid, type='photo', limit=1) | |
res_v = client.posts(uid, type='video', limit=1) | |
try: | |
tburl = clean_csv(res['blog']['url']) | |
title = clean_csv(res['blog']['title']) | |
posts = res['blog']['total_posts'] | |
photo = res_p['total_posts'] | |
video = res_v['total_posts'] | |
other = posts - (photo + video) | |
bdesc = re.sub(r"\n" , ' ', clean_csv(res['blog']['description'])) | |
utime = time.strftime('%Y-%m-%d', time.localtime(res['blog']['updated'])) | |
except KeyError: | |
tstr = 'ERROR:{s}Something is wrong with the following user id:{s}{id}' | |
output = tstr.format(s=',', id=uid) | |
else: | |
outl = tburl + ',' + title + ',' + uid + ',' + bdesc + ',' + str(posts) + ',' | |
output = outl + str(photo) + ',' + str(video) + ',' + str(other) + ',' + utime | |
print(output) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment