Website Formatter

website_formatter.py

import clipboard
import os
from pathlib import Path
import re


def apply_transforms(txt, list_of_trans):
    for trans in list_of_trans:
        txt = trans(txt)
    return txt


def replacer(txt, dict_of_replace):
    for rep in dict_of_replace.keys():
        txt = txt.replace(rep, dict_of_replace[rep])
    return txt

def regexreplacer(txt, dict_of_replace):
    for rep in dict_of_replace.keys():
        txt = re.sub(rep, dict_of_replace[rep], txt)
    return txt

def indent_transform(txt):
    l = txt.split("\n")
    return "\n".join([x.strip() for x in l])

def paragraph_converter(txt):
    l = txt.split("\n")
    for item in range(len(l)):
        if len(l[item])>0 and l[item][0] not in ["#"," ",]:
            l[item] = "- "+l[item]
    return "\n".join(l)

dict_of_replace = {
    #"*": "",
    "- **": "# ",
    "**": "",
    "****": "",
    "[latex]": "$",
    "[/latex]": "$",
    "<math>":"$",
    "</math>":"$",
    "__": "",
    "<h3>": "# [[",
    "</h3>": "]]",
    "<h1>": "[[",
    "</h1>": "]]",
    #"<h2>": "[[",
    #"</h2>": "]]",
    "<h2>": "# ",
    "</h2>": "",
    "“":"'",
    "”":"'",
    #". ": "\n",
    #":": "\n- ",

    # Wikipedia specific stuff
    ")>":"",
    #") ":" ",
    "#cite_note":" ",
    "(<https://en.wikipedia.org/wiki/":" ",
    "(https://en.wikipedia.org/wiki/":" ",
    "(<https://en.wikipedia.org/w/index.php?title=":" ",
    "(https://en.wikipedia.org/w/index.php?title=":" ",
    "s&action=edit&redlink=1":" ",

    # Pdfannots
    ">":"-",
}

dict_regex_replace = {
    r'\[.*?\]':"", #wiki links
    r' \* Page #.*\:':"", #pdfannots page numbers
}

text = clipboard.paste()
text = replacer(text, dict_of_replace)
text = regexreplacer(text, dict_regex_replace)
text = apply_transforms(text, [
    indent_transform,
    paragraph_converter,
])
clipboard.copy(text)