There is a plugin for Caliber book cataloger. in Windows it is not put because of requests and bs4. Please help rewrite without them. plugin is a python script

# -*- coding: utf-8 -*- from __future__ import (unicode_literals, division, absolute_import, print_function) import re from Queue import Queue, Empty import requests from bs4 import BeautifulSoup from calibre import as_unicode from calibre.utils.date import parse_only_date from calibre.ebooks.metadata import check_isbn from calibre.ebooks.metadata.book.base import Metadata from calibre.ebooks.metadata.sources.base import Source, Option class BookradarMetadataSourcePlugin(Source): name = 'Bookradar' capabilities = frozenset(['identify', 'cover']) touched_fields = frozenset(('title', 'authors', 'identifier:isbn', 'publisher', 'pubdate')) url_pattern = 'http://bookradar.org/search/?q=%s&type=all' @classmethod def find(cls, base_element, class_name, single=False): found = base_element.find_all('div', class_=class_name) if single: if not found: return '' return found[0].text.strip() return found @classmethod def parse_response(cls, response, title_initial, author_initial, isbn_initial, log): global page_soup metadata_items = [] page_soup = BeautifulSoup(response.text) for idx, candidate in enumerate(cls.find(page_soup, 'b-result'), 1): title = cls.find(candidate, 'b-result__name-wrap', True) author = map(unicode.strip, cls.find(candidate, 'b-result__author', True).split(',')) comments = cls.find(candidate, 'b-result__desc__full', True).replace(u'Скрыть', '').strip() isbn = cls.find(candidate, 'b-result__isbn', True).split(':')[-1].split(',')[0].strip() log.info(u'Found candidate %s: %s' % (idx, title)) publisher = None pubdate = None other_info = cls.find(candidate, 'b-result__years', True).strip() if other_info: for entry in other_info.split(';'): k, v = entry.split(':', 1) k = k.strip() if k == u'Год': pubdate = parse_only_date('1.1.%s' % v.split(',')[0].strip()) elif k == u'Издательство': publisher = v.strip() metadata_item = Metadata(title, author) metadata_item.isbn = isbn or isbn_initial if comments: metadata_item.comments = comments if publisher is not None: metadata_item.publisher = publisher if pubdate is not None: metadata_item.pubdate = pubdate metadata_items.append(metadata_item) return metadata_items def is_customizable(self): return False def identify(self, log, result_queue, abort, title=None, authors=None, identifiers=None, timeout=30): log.info(u'Bookradar identification started ...') identifiers = identifiers or {} search_tokens = [] if title: search_tokens += list(self.get_title_tokens(title)) if authors: search_tokens += list(self.get_author_tokens(authors, only_first_author=True)) isbn = check_isbn(identifiers.get('isbn', None)) if isbn: search_tokens += (isbn,) search_str = ' '.join(search_tokens) url = self.url_pattern % search_str log.info(u'Searching for: %s' % search_str) try: response = requests.get(url, timeout=timeout) except requests.exceptions.RequestException as e: log.exception('Failed to get data from `%s`: %s' % (url, e.message)) return as_unicode(e) metadata = self.parse_response(response, title, authors, isbn, log=log) for result in metadata: self.clean_downloaded_metadata(result) result_queue.put(result) def download_cover(self, log, result_queue, abort, title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False): # {{{ log.info(u'Bookradar identification started ...') identifiers = identifiers or {} search_tokens = [] cached_url = None if title: search_tokens += list(self.get_title_tokens(title)) isbn = check_isbn(identifiers.get('isbn', None)) if isbn: search_tokens += (isbn,) search_str = ' '.join(search_tokens) url = self.url_pattern % search_str log.info(u'Searching for: %s' % search_str) try: response = requests.get(url, timeout=timeout) except requests.exceptions.RequestException as e: log.exception('Failed to get data from `%s`: %s' % (url, e.message)) return as_unicode(e) page_soup = BeautifulSoup(response.text) emb = None for img in page_soup.findAll('img', src=True): emb = img['src'].strip() if emb.lower().endswith('.jpg') or emb.lower().endswith('.jpeg'): break if emb is None: log.info('No cover found') else: cached_url=emb log.info('Downloading cover from:', cached_url) try: cdata = self.browser.open_novisit(cached_url, timeout=timeout).read() if cdata: result_queue.put((self, cdata)) except Exception as e: log.exception(u'Failed to download cover from: %s'%cached_url) return as_unicode(e) if __name__ == '__main__': # Tests # calibre-customize -b . && calibre-debug -e __init__.py from calibre.ebooks.metadata.sources.test import (test_identify_plugin, title_test, authors_test, isbn_test) test_identify_plugin(BookradarMetadataSourcePlugin.name, [ ( {'identifiers': {'isbn': '9785932861578'}}, [ title_test(u'Python. Подробный справочник', exact=True), authors_test([u'Дэвид Бизли']) ] ), ( { 'title': u'справочник', 'identifiers': {'isbn': '9785932861578'} }, [ title_test(u'Python. Подробный справочник', exact=True), authors_test([u'Дэвид Бизли']) ] ), ( { 'title': u'Opencv Computer Vision', 'authors': u'Howse' }, [ title_test(u'Opencv Computer Vision with Python', exact=True), authors_test([u'Joseph Howse']) ] ), ])
  • Both requests and beautifulsoup4 are libraries written in pure Python (there should be no difficulty in using them on any system where python works at all). I am not familiar with how caliber is installed on Windows, try: calibre-debug -c 'import pip, sys; sys.exit(pip.main())' install requests beautifulsoup4 calibre-debug -c 'import pip, sys; sys.exit(pip.main())' install requests beautifulsoup4 run. - jfs

1 answer 1

Also encountered such a problem. Install the required requests and bs4 libraries. Then find their folders, requests and bs4 appropriately and add them to the pylib.zip archive, which lies at the root of Caliber.