def get_metadata(stream): """ Return basic meta-data about the LRF file in C{stream} as a L{MetaInformation} object. @param stream: A file like object or an instance of L{LRFMetaFile} """ lrf = stream if isinstance(stream, LRFMetaFile) else LRFMetaFile(stream) authors = string_to_authors(lrf.author) mi = MetaInformation(lrf.title.strip(), authors) mi.author = lrf.author.strip() mi.comments = lrf.free_text.strip() mi.category = lrf.category.strip() + ', ' + lrf.classification.strip() tags = [x.strip() for x in mi.category.split(',') if x.strip()] if tags: mi.tags = tags if mi.category.strip() == ',': mi.category = None mi.publisher = lrf.publisher.strip() mi.cover_data = lrf.get_cover() try: mi.title_sort = lrf.title_reading.strip() if not mi.title_sort: mi.title_sort = None except Exception: pass try: mi.author_sort = lrf.author_reading.strip() if not mi.author_sort: mi.author_sort = None except Exception: pass if not mi.title or 'unknown' in mi.title.lower(): mi.title = None if not mi.authors: mi.authors = None if not mi.author or 'unknown' in mi.author.lower(): mi.author = None if not mi.category or 'unknown' in mi.category.lower(): mi.category = None if not mi.publisher or 'unknown' in mi.publisher.lower() or \ 'some publisher' in mi.publisher.lower(): mi.publisher = None return mi
def get_metadata(stream): """ Return metadata as a L{MetaInfo} object """ stream.seek(0) if stream.read(5) != br'{\rtf': return MetaInformation('Unknown') block = get_document_info(stream)[0] if not block: return MetaInformation('Unknown') stream.seek(0) cpg = detect_codepage(stream) stream.seek(0) title_match = title_pat.search(block) if title_match is not None: title = decode(title_match.group(1).strip(), cpg) else: title = 'Unknown' author_match = author_pat.search(block) if author_match is not None: author = decode(author_match.group(1).strip(), cpg) else: author = None mi = MetaInformation(title) if author: mi.authors = [x.strip() for x in author.split(',')] comment_match = comment_pat.search(block) if comment_match is not None: comment = decode(comment_match.group(1).strip(), cpg) mi.comments = comment tags_match = tags_pat.search(block) if tags_match is not None: tags = decode(tags_match.group(1).strip(), cpg) mi.tags = list(filter(None, (x.strip() for x in tags.split(',')))) publisher_match = publisher_pat.search(block) if publisher_match is not None: publisher = decode(publisher_match.group(1).strip(), cpg) mi.publisher = publisher return mi
def metadata_from_filename(name, pat=None, fallback_pat=None): if isinstance(name, bytes): name = name.decode(filesystem_encoding, 'replace') name = name.rpartition('.')[0] mi = MetaInformation(None, None) if pat is None: pat = re.compile(prefs.get('filename_pattern')) name = name.replace('_', ' ') match = pat.search(name) if match is None and fallback_pat is not None: match = fallback_pat.search(name) if match is not None: try: mi.title = match.group('title') except IndexError: pass try: au = match.group('author') aus = string_to_authors(au) if aus: mi.authors = aus if prefs['swap_author_names'] and mi.authors: def swap(a): if ',' in a: parts = a.split(',', 1) else: parts = a.split(None, 1) if len(parts) > 1: t = parts[-1] parts = parts[:-1] parts.insert(0, t) return ' '.join(parts) mi.authors = [swap(x) for x in mi.authors] except (IndexError, ValueError): pass try: mi.series = match.group('series') except IndexError: pass try: si = match.group('series_index') mi.series_index = float(si) except (IndexError, ValueError, TypeError): pass try: si = match.group('isbn') mi.isbn = si except (IndexError, ValueError): pass try: publisher = match.group('publisher') mi.publisher = publisher except (IndexError, ValueError): pass try: pubdate = match.group('published') if pubdate: from ebook_converter.utils.date import parse_only_date mi.pubdate = parse_only_date(pubdate) except: pass try: comments = match.group('comments') mi.comments = comments except (IndexError, ValueError): pass if mi.is_null('title'): mi.title = name return mi
def get_metadata(stream, extract_cover=True): whitespace = re.compile(r'\s+') def normalize(s): return whitespace.sub(' ', s).strip() with ZipFile(stream) as zf: meta = zf.read('meta.xml') root = fromstring(meta) def find(field): ns, tag = fields[field] ans = root.xpath('//ns0:{}'.format(tag), namespaces={'ns0': ns}) if ans: return normalize( tostring(ans[0], method='text', encoding='unicode', with_tail=False)).strip() mi = MetaInformation(None, []) title = find('title') if title: mi.title = title creator = find('initial-creator') or find('creator') if creator: mi.authors = string_to_authors(creator) desc = find('description') if desc: mi.comments = desc lang = find('language') if lang and canonicalize_lang(lang): mi.languages = [canonicalize_lang(lang)] kw = find('keyword') or find('keywords') if kw: mi.tags = [x.strip() for x in kw.split(',') if x.strip()] data = {} for tag in root.xpath('//ns0:user-defined', namespaces={'ns0': fields['user-defined'][0]}): name = (tag.get('{%s}name' % METANS) or '').lower() vtype = tag.get('{%s}value-type' % METANS) or 'string' val = tag.text if name and val: if vtype == 'boolean': val = val == 'true' data[name] = val opfmeta = False # we need this later for the cover opfnocover = False if data.get('opf.metadata'): # custom metadata contains OPF information opfmeta = True if data.get('opf.titlesort', ''): mi.title_sort = data['opf.titlesort'] if data.get('opf.authors', ''): mi.authors = string_to_authors(data['opf.authors']) if data.get('opf.authorsort', ''): mi.author_sort = data['opf.authorsort'] if data.get('opf.isbn', ''): isbn = check_isbn(data['opf.isbn']) if isbn is not None: mi.isbn = isbn if data.get('opf.publisher', ''): mi.publisher = data['opf.publisher'] if data.get('opf.pubdate', ''): mi.pubdate = parse_date(data['opf.pubdate'], assume_utc=True) if data.get('opf.identifiers'): try: mi.identifiers = json.loads(data['opf.identifiers']) except Exception: pass if data.get('opf.rating'): try: mi.rating = max(0, min(float(data['opf.rating']), 10)) except Exception: pass if data.get('opf.series', ''): mi.series = data['opf.series'] if data.get('opf.seriesindex', ''): try: mi.series_index = float(data['opf.seriesindex']) except Exception: mi.series_index = 1.0 if data.get('opf.language', ''): cl = canonicalize_lang(data['opf.language']) if cl: mi.languages = [cl] opfnocover = data.get('opf.nocover', False) if not opfnocover: try: read_cover(stream, zf, mi, opfmeta, extract_cover) except Exception: pass # Do not let an error reading the cover prevent reading other data return mi