#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys, os, re

from sigil_bs4 import BeautifulSoup


def run(bk):

# get all html files
for (html_id, href) in bk.text_iter():

deletec=[]
deletem=[]

file_name = os.path.basename(href)
html = bk.readfile(html_id)

# convert html to soup
soup = BeautifulSoup(html, 'html.parser')
orig_html = str(soup)

# get all i,b,small,sup,sub,br,a,li tags with class='*calibre*' (containing all those characters, in fact)
tags = soup.find_all(['i', 'b', 'small', 'sub', 'sup', 'br', 'a', 'li'], class_=re.compile("calibre"))
for tag in tags:
theclass = tag['class'] # list under 'html.parser': can be multivalued
if len(theclass) == 1: # not a multivalued class
# remove class attribute
deletec = deletec + [(tag.name, theclass)]
del tag['class']
# else: # remove the *calibre* style from class? How?

# this clears the plug-in console: add after
metas = soup.find_all('meta', attrs={'name': True})
for meta in metas:
# exclude 'calibre:cover', remove others
if not 'cover' in meta['name']: # works here: string, and NOT above: list
deletem = deletem + [(meta.name, meta['name'])]
meta.decompose() # all previous print statements lost here

# update file with changes
if str(soup) != orig_html:
bk.writefile(html_id, str(soup))
# write a list of changes for checking
print(deletec, sep=' ')
print(deletem, sep=' ')
print(file_name, 'updated')

print('Done')
return 0

def main():
print("I reached main when I should not have")
return -1

if __name__ == "__main__":
sys.exit(main())