Generating epubs.

gragir/enrich_html.py

@@ -2,6 +2,7 @@ import logging
 import urllib
 import os
 from bs4 import BeautifulSoup
+import cssutils
 
 from book import Item, Book
 
@@ -31,6 +32,8 @@ class EnrichHtml(object):
                     item.title = item.soup.title.string
                 else:
                     logger.info("No title for {}".format(item.url))
+            elif item.content_type == 'text/css':
+                item.css = cssutils.parseString(item.payload, None, item.url)
             else:
                 logger.info("Skipping {} {}".format(item.content_type, item.url))
 
@@ -80,6 +83,19 @@ class EnrichHtml(object):
                 else:
                     logger.warn("  No content found: {}".format(item.url))
                     remove.append(item)
+                # Remove annotator
+                remove_content = []
+                remove_content.extend(item.soup.find_all('div', attrs={"class": "annotator-outer"}))
+                remove_content.extend(item.soup.find_all('div', attrs={"class": "annotator-modal-wrapper"}))
+                remove_content.extend(item.soup.find_all('div', attrs={"class": "annotator-adder"}))
+                for elem in remove_content:
+                    elem.decompose()
+                # Unwrap
+                remove_content = []
+                remove_content.extend(item.soup.find_all('div', attrs={"class": "annotator-wrapper"}))
+                remove_content.extend(item.soup.find_all('div', attrs={"id": "sbo-rt-content"}))
+                for elem in remove_content:
+                    elem.unwrap()
 
         for item in remove:
             book.remove(item)
@@ -95,14 +111,14 @@ class EnrichHtml(object):
                 links = item.soup.find_all('a', attrs={"class": "prev nav-link"})
                 if len(links):
                     item.prev = book.content[
-                                    item.getAbsoluteUrl(links[0]['href'])]
+                                    item.getAbsoluteUrl(links[0].get('href'))]
                     logger.info("  prev = {}:".format(item.prev.url))
 
                 # Try to get next chapter.
                 links = item.soup.find_all('a', attrs={"class": "next nav-link"})
                 if len(links):
                     item.next = book.content[
-                                    item.getAbsoluteUrl(links[0]['href'])]
+                                    item.getAbsoluteUrl(links[0].get('href'))]
                     logger.info("  next = {}:".format(item.next.url))
 
     @classmethod

gragir/prepare_epub.py

@@ -2,6 +2,7 @@ import os
 import logging
 import urllib
 from bs4 import BeautifulSoup
+from tidylib import tidy_document
 
 from book import Item, Book
 
@@ -33,6 +34,13 @@ class PrepareEpub(object):
 
             elif mime == 'text/html':
                 local_url = cls._createLocalName(book,item,'')
+                local_url_split = local_url.split('.')
+                logger.info('{}'.format(local_url_split))
+                if local_url_split[-1] == 'htm' \
+                    or local_url_split[-1] == 'html':
+                    local_url_split[-1] = 'xhtml'
+                    local_url = '.'.join(local_url_split)
+                    logger.info('converting to xhtml {}'.format(local_url_split))
             else:
                 local_url = cls._createLocalName(book,item,mime.split("/")[0])
 
@@ -105,4 +113,7 @@ class PrepareEpub(object):
         logger = logging.getLogger(__name__)
         logger.info("Createing XML for {}".format(item.url))
 
-        item.payload = item.soup.prettify("utf-8")
+        item.payload, err = tidy_document( item.soup.prettify("utf-8"),
+                options={ 'output-xhtml' : 1, 'tidy-mark' : 1})
+        item.content_type = 'text/xhtml'
+        logger.info("Errors: {}".format(err))

gragir/save_epub.py

@@ -14,6 +14,8 @@ class SaveEpub(object):
 
         ebook = ebooklib.EpubBook()
         cls.fillEpubBook(ebook, book)
+        cls.fillSpine(ebook, book)
+        cls.fillGuide(ebook, book)
         cls.writeEpubBook(book.file_name, ebook)
 
 
@@ -31,6 +33,8 @@ class SaveEpub(object):
         """
         logger = logging.getLogger(__name__)
 
+        options = {'plugins': []}
+
         try:
             epub = ebooklib.EpubWriter(name, ebook, options)
             epub.process()
@@ -54,7 +58,7 @@ class SaveEpub(object):
                 or mime == 'application/font-woff2':
             return 'font'
 
-        elif mime == 'text/html':
+        elif mime == 'text/html' or mime == 'text/xhtml':
             return 'html'
 
         else:
@@ -93,9 +97,39 @@ class SaveEpub(object):
             eitem.content = item.payload
 
             ebook.add_item(eitem)
-            item.id = eitem.get_id()
+            item.idref = eitem.get_id()
 
-        #     class EpubNav(EpubHtml):
-        #     class EpubNcx(EpubItem):
-        #     class Link(object):
-        #     class Section(object):
+    @classmethod
+    def fillSpine(cls, ebook, book):
+        logger = logging.getLogger(__name__)
+
+        ebook.add_item(ebooklib.EpubNcx())
+        ebook.add_item(ebooklib.EpubNav())
+
+        # define CSS style
+        style = 'BODY {color: white;}'
+        nav_css = ebooklib.EpubItem(uid="style_nav", file_name="style/nav.css", media_type="text/css", content=style)
+        ebook.add_item(nav_css)
+        ebook.spine = ['nav']
+
+        # ebook.toc = (ebooklib.Link(item.url, item.title, 'intro'),
+        #      (epub.Section(item.title),
+        #      (c1, ))
+        #     )
+
+        item = book.first
+        while item:
+            logger.info("EPUB: Adding to spin {}".format(item.url))
+            ebook.spine.append(item.idref)
+
+            if hasattr(item, 'next'):
+                item = item.next
+            else:
+                item = None
+
+    @classmethod
+    def fillGuide(cls, ebook, book):
+        logger = logging.getLogger(__name__)
+
+        item = book.first
+        ebook.guide.append({ 'href' : item.url, 'title' : item.title, 'type' : 'text'})