blag/md_get_wp_links.py
2020-04-11 22:25:33 -04:00

56 lines
2.0 KiB
Python
Executable File

#!/usr/bin/env python3
import re
import sys
import os
search_dir = "/home/hodapp/source/blag/wp-content-old/"
search_hints = ["uploads"]
dest_dir = "/home/hodapp/source/blag/hugo_blag/static/wp_old"
dest_rel = ["/wp_old"]
# Matches text like http://.../wp-content/... wrapped in ( and ).
# Group 1 is the URL itself.
# Group 2 is the base filename (without path).
#link_re = re.compile(r"\((http[^)]+)\)")
link_re = re.compile(r"\((http[^)]+/([^).]+\.(jpg|jpeg|JPG|JPEG|gif|GIF|png|PNG)))\)")
#for n,line in enumerate(sys.stdin):
replacements = {}
data = []
for n,line in enumerate(open(sys.argv[1], "r")):
data.append(line)
for url,base,_ in link_re.findall(line):
print("# line {}: url={} base={}".format(n, url, base))
parts = url.split("/")
# Walk *backwards* from filename, adding one part of the path
# at a time, and try to find a file by this name in
# 'search_dir' (and with 'search_hints' added one at a time):
found = None
for i in range(1,len(parts)+1):
if found is not None:
break
for j in range(len(search_hints) + 1):
rel = parts[-i:]
p = os.path.join(search_dir, *(search_hints[:j] + rel))
#print("try path: {}".format(p))
if os.path.isfile(p):
print("# found file: {}".format(p))
dst = os.path.join(dest_dir, *rel)
print("mkdir -p {}".format(os.path.join(dest_dir, *rel[:-1])))
print("cp {} {}".format(p, dst))
rel_dst = os.path.join(*(dest_rel + rel))
print("# Map {} to {}".format(url, rel_dst))
replacements[url] = rel_dst
found = p
break
if found is None:
print("# *** not found")
with open(sys.argv[2], "w+") as f:
for line in data:
for k in replacements:
line = line.replace(k, replacements[k])
f.write(line)