Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

EPUB Input: Automatically extract cover image from simple HTML title page that consists of only a single <img> tag

Browse Source
This commit is contained in:
Kovid Goyal 2012-04-12 19:10:56 +05:30
parent 63d578f99b
commit 24925ddbf9
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
src/calibre/ebooks/__init__.py
View File

@ -93,6 +93,20 @@ def extract_calibre_cover(raw, base, log):
if os.path.exists(img):
return open(img, 'rb').read()
# Look for a simple cover, i.e. a body with no text and only one <img> tag
if matches is None:
body = soup.find('body')
if body is not None:
text = u''.join(map(unicode, body.findAll(text=True)))
if text.strip():
# Body has text, abort
return
images = body.findAll('img', src=True)
if 0 < len(images) < 2:
img = os.path.join(base, *images[0]['src'].split('/'))
if os.path.exists(img):
return open(img, 'rb').read()
def render_html_svg_workaround(path_to_html, log, width=590, height=750):
from calibre.ebooks.oeb.base import SVG_NS
raw = open(path_to_html, 'rb').read()
@ -108,6 +122,7 @@ def render_html_svg_workaround(path_to_html, log, width=590, height=750):
data = extract_calibre_cover(raw, os.path.dirname(path_to_html), log)
except:
pass
if data is None:
renderer = render_html(path_to_html, width, height)
data = getattr(renderer, 'data', None)