def run(project_name, data_dir, book_dir, epub_dir, books_file, failure_books, target_dir, category='', book_format='epub3'):
# rename success products
if not os.path.exists(book_dir):
raise Exception('product book directory not exists')
if not os.path.exists(data_dir):
raise Exception('data directory not exists')
if not os.path.exists(epub_dir):
raise Exception('epub directory not exists')
if not os.path.exists(books_file):
raise Exception('books file not exists')
for fname in os.listdir(book_dir):
name, ext = os.path.splitext(fname)
if category:
new_fname = '_'.join([name, project_name, category, book_format]) + ext
else:
new_fname = '_'.join([name, project_name, book_format]) + ext
shutil.move(os.sep.join([book_dir, fname]), os.sep.join([book_dir, new_fname]))
# move failure books
books = Books.create_from_file(books_file)
new_books = Books()
target_books_file = os.sep.join([target_dir, 'books.jl'])
for book in failure_books:
bookname = book['bookname']
filename = book['filename']
dirname = os.path.splitext(filename)[0]
source_data_file = os.sep.join([data_dir, filename])
target_data_file = os.sep.join([target_dir, filename])
source_epub_dir = os.sep.join([epub_dir, dirname])
target_epub_dir = os.sep.join([target_dir, dirname])
if not os.path.exists(target_epub_dir):
shutil.copytree(source_epub_dir, target_epub_dir)
if not os.path.exists(target_data_file):
shutil.copy(source_data_file, target_data_file)
bk = books.get_book(filename)
if bk:
new_books.add_book(bk, True)
new_books.dump_to_file(target_books_file)
def run(source_dir, target_dir, books_file, sitename, bookformat):
if not os.path.exists(source_dir):
raise Exception('source directory not exists: %s' % source_dir)
if not os.path.exists(target_dir):
raise Exception('target directory not exists: %s' % target_dir)
if not os.path.exists(books_file):
raise Exception('books file not exists: %s' % books_file)
bookinfo = {}
books = Books()
for bk in Books.create_from_file(books_file).get_books():
en_name = bk.get_en_name()
if en_name in bookinfo:
raise Exception('book en_name duplicate: %s' % en_name)
if not bk.get_filename():
bk.set_filename(en_name+'.jl')
bk.set_sitename(sitename)
bk.set_format(bookformat)
bookinfo[en_name] = bk
data_count = 0
other_count = 0
whitelist = set(['books.jl'])
for fname in os.listdir(source_dir):
source_file = os.sep.join([source_dir, fname])
if os.path.isdir(source_file):
continue
if fname in whitelist:
continue
if fname.endswith('.jl'):
# source_file = os.sep.join([source_dir, fname])
target_file = os.sep.join([target_dir, fname])
article_count = 0
word_count = 0
bookname = os.path.splitext(fname)[0]
category = ''
sub_category = ''
with open(source_file, 'r', encoding='utf8') as rf, open(target_file, 'w', encoding='utf8') as wf:
for line in rf:
line = line.strip()
if not line:
continue
article = json.loads(line)
article['title'] = clean_article_title(article['title'])
article['content'], count = clean_article_content(article['content'])
wf.write(json.dumps(article, ensure_ascii=False)+'\n')
article_count += 1
word_count += count
if not category:
category = article.get('category', '')
if not sub_category:
sub_category = article.get('sub_category', '')
if not bookname:
raise Exception('data json has no book field')
if bookname not in bookinfo:
raise Exception('books file has no [%s]' % bookname)
bk = bookinfo[bookname]
bk.set_category(category)
bk.set_sub_category(sub_category)
bk.set_articlecount(article_count)
bk.set_wordcount(word_count)
books.add_book(bk)
data_count += 1
else:
shutil.copy(source_file, target_dir)
other_count += 1
books.dump_to_file(os.sep.join([target_dir, 'books.jl']))
return [data_count, other_count]
