notes/slate_starchive.py

   1 import os
   2 import re
   3 import requests
   4 import sys
   5
   6
   7 slate_sturl_regex = re.compile(r"https?://slatestarcodex.com/\d{4}/\d{2}/\d{2}/[-a-z0-9]+/")
   8
   9
  10 def slate_starchive_post_content(content):
  11     slate_star_links = slate_sturl_regex.finditer(content)
  12     revised = content
  13     for match in slate_star_links:
  14         link_url = match.group()
  15         archive_response = requests.get(
  16             "http://archive.org/wayback/available?url={}".format(link_url)
  17         )
  18         try:
  19             archive_url = archive_response.json()['archived_snapshots']['closest']['url']
  20         except KeyError:
  21             print(
  22                 "didn't successfully get an archive link for {}: {}".format(
  23                     link_url, archive_response.text
  24                 )
  25             )
  26         else:
  27             print("replacing \033[93m{}\033[0m with \033[92m{}\033[0m".format(link_url, archive_url))
  28             revised = revised.replace(link_url, archive_url)
  29     return revised
  30
  31
  32 def tree(root):
  33     for path, _dirs, filenames in os.walk(root):
  34         for filename in filenames:
  35             if not filename.endswith(".md"):
  36                 continue
  37             filepath = os.path.join(path, filename)
  38             with open(filepath) as f:
  39                 print("examining {}".format(filepath))
  40                 content = f.read()
  41                 revised = slate_starchive_post_content(content)
  42             if revised != content:
  43                 with open(filepath, 'w') as g:
  44                     print("revising {}".format(filepath))
  45                     g.write(revised)
  46
  47
  48 if __name__ == "__main__":
  49     tree(sys.argv[1])