#!/usr/bin/env python3
"""Extract Html content from an EPUB file (.chm), concatenating all sections"""
from __future__ import print_function
import sys
import os
import re
import rclexecm
from rclbasehandler import RclBaseHandler
sys.path.append(sys.path[0]+"/recollepub.zip")
try:
import epub
except:
print("RECFILTERROR HELPERNOTFOUND python3:epub")
sys.exit(1);
class EPUBConcatExtractor(RclBaseHandler):
"""RclExecM slave worker for extracting all text from an EPUB
file. This version concatenates all nodes."""
def __init__(self, em):
super(EPUBConcatExtractor, self).__init__(em)
def _header(self):
meta = self.book.opf.metadata
title = ""
for tt, lang in meta.titles:
title += tt + " "
author = ""
for name, role, fileas in meta.creators:
author += name + " "
data = "\n\n"
if title:
data += "" + self.em.htmlescape(title) + "\n"
if author:
data += '\n'
if meta.description:
data += '\n'
data += ""
data = data.encode('UTF-8')
return data
def html_text(self, fn):
"""Extract EPUB data as concatenated HTML"""
f = open(fn, 'rb')
self.book = epub.open_epub(f)
data = self._header()
ids = []
if self.book.opf.spine:
for id, linear in self.book.opf.spine.itemrefs:
ids.append(id)
else:
for id, item in self.book.opf.manifest.items():
ids.append(id)
for id in ids:
item = self.book.get_item(id)
if item is None or item.media_type != 'application/xhtml+xml':
continue
doc = self.book.read_item(item)
doc = re.sub(b'''<\?.*\?>''', b'', doc)
doc = re.sub(b'''<[hH][tT][mM][lL].*<[bB][oO][dD][yY][^>]*>''',
b'', doc, 1, re.DOTALL)
doc = re.sub(b'''''', b'', doc)
doc = re.sub(b'''''', b'', doc)
data += doc
data += b''
return data
proto = rclexecm.RclExecM()
extract = EPUBConcatExtractor(proto)
rclexecm.main(proto, extract)