Merge branch 'lemmsh-upload_more_than_pdf'

Merging PR #30

cps/book_formats.py

@@ -0,0 +1,99 @@
+__author__ = 'lemmsh'
+
+import logging
+logger = logging.getLogger("book_formats")
+
+import uploader
+import os
+try:
+    from wand.image import Image
+    use_generic_pdf_cover = False
+except ImportError, e:
+    logger.warning('cannot import Image, generating pdf covers for pdf uploads will not work: %s', e)
+    use_generic_pdf_cover = True
+try:
+    from PyPDF2 import PdfFileReader
+    use_pdf_meta = True
+except ImportError, e:
+    logger.warning('cannot import PyPDF2, extracting pdf metadata will not work: %s', e)
+    use_pdf_meta = False
+
+try:
+    import epub
+    use_epub_meta = True
+except ImportError, e:
+    logger.warning('cannot import epub, extracting epub metadata will not work: %s', e)
+    use_epub_meta = False
+
+try:
+    import fb2
+    use_fb2_meta = True
+except ImportError, e:
+    logger.warning('cannot import fb2, extracting fb2 metadata will not work: %s', e)
+    use_fb2_meta = False
+
+
+def process(tmp_file_path, original_file_name, original_file_extension):
+    try:
+        if ".PDF" == original_file_extension.upper():
+            return pdf_meta(tmp_file_path, original_file_name, original_file_extension)
+        if ".EPUB" == original_file_extension.upper() and use_epub_meta == True:
+            return epub.get_epub_info(tmp_file_path, original_file_name, original_file_extension)
+        if ".FB2" == original_file_extension.upper() and use_fb2_meta == True:
+            return fb2.get_fb2_info(tmp_file_path, original_file_name, original_file_extension)
+    except Exception, e:
+        logger.warning('cannot parse metadata, using default: %s', e)
+
+    return default_meta(tmp_file_path, original_file_name, original_file_extension)
+
+
+
+def default_meta(tmp_file_path, original_file_name, original_file_extension):
+    return uploader.BookMeta(
+        file_path = tmp_file_path,
+        extension = original_file_extension,
+        title = original_file_name,
+        author = "Unknown",
+        cover = None,
+        description = "",
+        tags = "",
+        series = "",
+        series_id="")
+
+
+def pdf_meta(tmp_file_path, original_file_name, original_file_extension):
+
+    if (use_pdf_meta):
+        pdf = PdfFileReader(open(tmp_file_path, 'rb'))
+        doc_info = pdf.getDocumentInfo()
+    else:
+        doc_info = None
+
+    if (doc_info is not None):
+        author = doc_info.author
+        title = doc_info.title
+        subject = doc_info.subject
+    else:
+        author = "Unknown"
+        title = original_file_name
+        subject = ""
+    return uploader.BookMeta(
+        file_path = tmp_file_path,
+        extension = original_file_extension,
+        title = title,
+        author = author,
+        cover = pdf_preview(tmp_file_path, original_file_name),
+        description = subject,
+        tags = "",
+        series = "",
+        series_id="")
+
+def pdf_preview(tmp_file_path, tmp_dir):
+    if use_generic_pdf_cover:
+        return None
+    else:
+        cover_file_name = os.path.splitext(tmp_file_path)[0] + ".cover.jpg"
+        with Image(filename=tmp_file_path + "[0]", resolution=150) as img:
+            img.compression_quality = 88
+            img.save(filename=os.path.join(tmp_dir, cover_file_name))
+        return cover_file_name

cps/epub.py

@@ -0,0 +1,67 @@
+import zipfile
+from lxml import etree
+import os
+import uploader
+
+def extractCover(zip, coverFile, tmp_file_name):
+    if (coverFile is None):
+        return None
+    else:
+        cf = zip.read("OPS/" + coverFile)
+        prefix = os.path.splitext(tmp_file_name)[0]
+        tmp_cover_name = prefix + "." + coverFile
+        image = open(tmp_cover_name, 'wb')
+        image.write(cf)
+        image.close()
+        return tmp_cover_name
+
+
+
+def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
+    ns = {
+        'n':'urn:oasis:names:tc:opendocument:xmlns:container',
+        'pkg':'http://www.idpf.org/2007/opf',
+        'dc':'http://purl.org/dc/elements/1.1/'
+    }
+
+    zip = zipfile.ZipFile(tmp_file_path)
+
+    txt = zip.read('META-INF/container.xml')
+    tree = etree.fromstring(txt)
+    cfname = tree.xpath('n:rootfiles/n:rootfile/@full-path',namespaces=ns)[0]
+
+    cf = zip.read(cfname)
+    tree = etree.fromstring(cf)
+
+    p = tree.xpath('/pkg:package/pkg:metadata',namespaces=ns)[0]
+
+    epub_metadata = {}
+    for s in ['title', 'description', 'creator']:
+        tmp = p.xpath('dc:%s/text()'%(s),namespaces=ns)
+        if (len(tmp) > 0):
+            epub_metadata[s] = p.xpath('dc:%s/text()'%(s),namespaces=ns)[0]
+        else:
+            epub_metadata[s] = "Unknown"
+
+    coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover']/@href",namespaces=ns)
+    if (len(coversection) > 0):
+        coverfile = extractCover(zip, coversection[0], tmp_file_path)
+    else:
+        coverfile = None
+    if epub_metadata['title'] is None:
+        title = original_file_name
+    else:
+        title = epub_metadata['title']
+
+
+    return uploader.BookMeta(
+        file_path = tmp_file_path,
+        extension = original_file_extension,
+        title = title,
+        author = epub_metadata['creator'],
+        cover = coverfile,
+        description = epub_metadata['description'],
+        tags = "",
+        series = "",
+        series_id="")
+

cps/fb2.py

@@ -0,0 +1,35 @@
+
+from lxml import etree
+import os
+import uploader
+
+
+def get_fb2_info(tmp_file_path, original_file_name, original_file_extension):
+
+    ns = {
+        'fb':'http://www.gribuser.ru/xml/fictionbook/2.0',
+        'l':'http://www.w3.org/1999/xlink',
+    }
+
+    fb2_file = open(tmp_file_path)
+    tree = etree.fromstring(fb2_file.read())
+
+    authors = tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:author', namespaces=ns)
+    def get_author(element):
+        return element.xpath('fb:first-name/text()', namespaces=ns)[0] + ' ' + element.xpath('fb:middle-name/text()', namespaces=ns)[0] + ' ' + element.xpath('fb:last-name/text()', namespaces=ns)[0]
+    author = ", ".join(map(get_author, authors))
+
+    title = unicode(tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:book-title/text()', namespaces=ns)[0])
+    description = unicode(tree.xpath('/fb:FictionBook/fb:description/fb:publish-info/fb:book-name/text()', namespaces=ns)[0])
+
+    return uploader.BookMeta(
+        file_path = tmp_file_path,
+        extension = original_file_extension,
+        title = title,
+        author = author,
+        cover = None,
+        description = description,
+        tags = "",
+        series = "",
+        series_id="")
+

cps/uploader.py

@@ -0,0 +1,30 @@
+import os
+import hashlib
+from collections import namedtuple
+import book_formats
+
+
+tmp_dir = "/tmp/calibre-web"
+
+BookMeta = namedtuple('BookMeta', 'file_path, extension, title, author, cover, description, tags, series, series_id')
+
+
+"""
+ :rtype: BookMeta
+"""
+def upload(file):
+    if not os.path.isdir(tmp_dir):
+        os.mkdir(tmp_dir)
+
+    filename = file.filename
+    filename_root, file_extension = os.path.splitext(filename)
+    md5 = hashlib.md5()
+    md5.update(filename)
+    tmp_file_path = os.path.join(tmp_dir, md5.hexdigest())
+    file.save(tmp_file_path)
+    meta = book_formats.process(tmp_file_path, filename_root, file_extension)
+    return meta
+
+
+
+

cps/web.py

@@ -25,11 +25,6 @@ from sqlalchemy.sql import *
 import json
 import datetime
 from uuid import uuid4
-try:
-    from wand.image import Image
-    use_generic_pdf_cover = False
-except ImportError, e:
-    use_generic_pdf_cover = True
 from shutil import copyfile
 
 class ReverseProxied(object):
@@ -78,6 +73,9 @@ file_handler.setLevel(logging.INFO)
 file_handler.setFormatter(formatter)
 app.logger.addHandler(file_handler)
 app.logger.info('Starting Calibre Web...')
+logging.getLogger("book_formats").addHandler(file_handler)
+logging.getLogger("book_formats").setLevel(logging.INFO)
+
 
 Principal(app)
 
@@ -1123,6 +1121,9 @@ def edit_book(book_id):
     else:
         return render_template('edit_book.html', book=book, authors=author_names, cc=cc)
 
+import uploader
+from shutil import move
+
 @app.route("/upload", methods = ["GET", "POST"])
 @login_required
 @upload_required
@@ -1134,20 +1135,16 @@ def upload():
     db.session.connection().connection.connection.create_function('uuid4', 0, lambda : str(uuid4()))
     if request.method == 'POST' and 'btn-upload' in request.files:
         file = request.files['btn-upload']
-        filename = file.filename
+        meta = uploader.upload(file)
-        filename_root, fileextension = os.path.splitext(filename)
+
-        if fileextension.upper() == ".PDF":
+        title = meta.title
-            title = filename_root
+        author = meta.author
-            author = "Unknown"
+
-        else: 
-            flash("Upload is only available for PDF files", category="error")
-            return redirect(url_for('index', _external=True))
-        
         title_dir = helper.get_valid_filename(title, False)
         author_dir = helper.get_valid_filename(author.decode('utf-8'), False)
         data_name = title_dir
         filepath = config.DB_ROOT + "/" + author_dir + "/" + title_dir
-        saved_filename = filepath + "/" + data_name + fileextension
+        saved_filename = filepath + "/" + data_name + meta.extension
         if not os.path.exists(filepath):
             try:
                 os.makedirs(filepath)
@@ -1155,21 +1152,20 @@ def upload():
                 flash("Failed to create path %s (Permission denied)." % filepath, category="error")
                 return redirect(url_for('index', _external=True))
         try:
-            file.save(saved_filename)
+            move(meta.file_path, saved_filename)
         except OSError:
             flash("Failed to store file %s (Permission denied)." % saved_filename, category="error")
             return redirect(url_for('index', _external=True))
+
         file_size = os.path.getsize(saved_filename)
-        has_cover = 0
+        if meta.cover is None:
-        if fileextension.upper() == ".PDF":
+            has_cover = 0
-            if use_generic_pdf_cover:
+            basedir = os.path.dirname(__file__)
-                basedir = os.path.dirname(__file__)
+            copyfile(os.path.join(basedir, "static/generic_cover.jpg"), os.path.join(filepath, "cover.jpg"))
-                copyfile(os.path.join(basedir, "static/generic_cover.jpg"), os.path.join(filepath, "cover.jpg"))
+        else:
-            else:
+            has_cover = 1
-                with Image(filename=saved_filename + "[0]", resolution=150) as img:
+            move(meta.cover, os.path.join(filepath, "cover.jpg"))
-                    img.compression_quality = 88
+
-                    img.save(filename=os.path.join(filepath, "cover.jpg"))
-                    has_cover = 1
         is_author = db.session.query(db.Authors).filter(db.Authors.name == author).first()
         if is_author:
             db_author = is_author
@@ -1179,7 +1175,7 @@ def upload():
         path = os.path.join(author_dir, title_dir)
         db_book = db.Books(title, "", "", datetime.datetime.now(), datetime.datetime(101, 01,01), 1, datetime.datetime.now(), path, has_cover, db_author, [])
         db_book.authors.append(db_author)
-        db_data = db.Data(db_book, fileextension.upper()[1:], file_size, data_name)
+        db_data = db.Data(db_book, meta.extension.upper()[1:], file_size, data_name)
         db_book.data.append(db_data)
         
         db.session.add(db_book)