Created
July 29, 2018 18:18
-
-
Save AlphaGit/9f909745d7c573146e6102ad65cc8149 to your computer and use it in GitHub Desktop.
Loading tumblr posts
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
# inspired in https://github.com/veggiedefender/miraculousladybot/blob/master/log.py | |
import requests | |
import re | |
import tumblr_client | |
from html2text import html2text | |
from datetime import datetime | |
from settings import blogs_to_search, posts_per_blog, tags_to_search, posts_per_search | |
def append_to_file(filename, contents): | |
with open(filename, 'a', encoding='utf8') as file: | |
file.writelines(contents + '\n') | |
def clean_up(text): | |
# well see this one later | |
return text | |
def get_posts(search_function, search_parameter, post_search_limit): | |
total = 0 | |
earliest = int(datetime.now().timestamp()) | |
iterations_without_posts = 0 | |
while total <= post_search_limit and iterations_without_posts < 5: | |
posts = search_function(search_parameter, earliest) | |
if len(posts) > 0: | |
earliest = min([ post["timestamp"] for post in posts ]) | |
else: | |
break | |
posts = [ post for post in posts if post["type"] == "text" ] | |
if len(posts) == 0: | |
iterations_without_posts += 1 | |
for post in posts: | |
body = html2text(post["body"]) | |
text = clean_up(body) | |
if len(text) == 0: | |
continue | |
append_to_file('text_source.txt', text) | |
total += 1 | |
for blog in blogs_to_search: | |
get_posts(tumblr_client.get_posts_from_blog, blog, posts_per_blog) | |
for tag in tags_to_search: | |
get_posts(tumblr_client.get_posts_from_search, tag, posts_per_search) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment