def parse_fb2(file_name: Path, get_transitions_func: Callable = None, coin_flip: List[str] = None):
print(file_name)
root = parse(file_name.read_bytes())
book = parse_book_info(root)
# print('book:', book)
print('title:', book.title)
print('author:', book.author)
print('annotation:', repr(book.annotation))
print('coverpage_id:', book.coverpage_id)
print('sequence_name:', book.sequence_name)
print('sequence_num:', book.sequence_num)
print('publisher:', book.publisher)
print('images:', list(book.images))
dir_book = DIR_DUMP_BOOKS / file_name.name
for section in root.select('body > section'):
section_id = clear_number(section.select_one('title > p'))
if not section_id:
section_id = "0"
# Удаление тегов-заголовков с номерами страниц
for title in section.select('title'):
title.decompose()
tags = section.find_all(recursive=False)
if get_transitions_func:
transitions = get_transitions_func(tags)
else:
transitions = get_transitions(tags)
images = get_images(tags)
preprocess_tags(tags)
section_tag = parse(''.join(map(str, tags)))
html_section = get_section_text(section_tag, None if section_id == '0' else section_id)
if coin_flip:
is_coin_flip = section in coin_flip
else:
is_coin_flip = False
book.add_section(
id=section_id,
text=html_section,
transitions=transitions,
images=images,
coin_flip=is_coin_flip,
)
print('sections:', len(book.sections))
book.save(dir_book)
from tools.parsers.book import parse_book_info
from tools.parsers.utils import (
parse, get_section_text, preprocess_tags, get_transitions, clear_number, get_images, DIR
)
# Страницы, в которых нужно монету подбрасывать
COIN_FLIP = [
'52'
]
file_name = DIR / 'Ужастики-2' / 'Stayn_Beregis-Lilovoy-Pasty-_RuLit_Me.fb2'
print(file_name)
root = parse(file_name.read_bytes())
book = parse_book_info(root)
# print('book:', book)
print('title:', book.title)
print('author:', book.author)
print('annotation:', repr(book.annotation))
print('coverpage_id:', book.coverpage_id)
print('sequence_name:', book.sequence_name)
print('sequence_num:', book.sequence_num)
print('publisher:', book.publisher)
print('images:', list(book.images))
dir_book = DIR_DUMP_BOOKS / file_name.name
section_by_tags = defaultdict(list)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
__author__ = 'ipetrash'
from pathlib import Path
from tools.parsers.utils import parse
for file_name in Path('Ужастики-2').glob('*.fb2'):
root = parse(file_name.read_bytes())
title_info_tag = root.select_one('description > title-info')
sequence_tag = title_info_tag.select_one('sequence')
sequence_name = sequence_tag.get('name') if sequence_tag else None
try:
sequence_num = sequence_tag.get('number') if sequence_tag else None
sequence_num = int(sequence_num)
except:
sequence_num = None
print('{:4}'.format(str(sequence_num)), file_name)
def parse_fb2(file_name: Path, coin_flip: List[str]):
print(file_name)
root = parse(file_name.read_bytes())
book = parse_book_info(root)
# print('book:', book)
print('title:', book.title)
print('author:', book.author)
print('annotation:', repr(book.annotation))
print('coverpage_id:', book.coverpage_id)
print('sequence_name:', book.sequence_name)
print('sequence_num:', book.sequence_num)
print('publisher:', book.publisher)
print('images:', list(book.images))
dir_book = DIR_DUMP_BOOKS / file_name.name
section_by_tags = defaultdict(list)
tags = None
for tag in root.select_one('body > section').children:
# If tag is not NavigableString
if not tag.name:
continue
if is_start_section(tag):
section = get_plaintext(tag)
tags = []
section_by_tags[section] = tags
continue
if tags is not None:
tags.append(tag)
end_number = 0
link_to_section = 0
for section, tags in section_by_tags.items():
transitions = get_transitions(tags)
images = get_images(tags)
if not transitions:
end_number += 1
link_to_section += len(transitions)
preprocess_tags(tags)
section_tag = parse(''.join(map(str, tags)))
html_section = get_section_text(section_tag, section)
book.add_section(id=section,
text=html_section,
transitions=transitions,
images=images,
coin_flip=section in coin_flip)
print('sections:', len(book.sections))
book.save(dir_book)