zacc806
/
pdfminer.six
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fixed: HTMLConverter.

pull/1/head
Yusuke Shinyama 2013-10-25 18:10:40 +09:00
parent a1cae26a74
commit 02ad086f6a
1 changed files with 14 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
pdfminer/converter.py
View File

@ -204,7 +204,7 @@ class HTMLConverter(PDFConverter):
}
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None,
scale=1, fontscale=0.7, layoutmode='normal', showpageno=True,
scale=1, fontscale=1.0, layoutmode='normal', showpageno=True,
pagemargin=50, imagewriter=None,
rect_colors={'curve':'black', 'page':'gray'},
text_colors={'char':'black'}):
@ -279,7 +279,7 @@ class HTMLConverter(PDFConverter):
self.write('</span>\n')
return
def begin_textbox(self, color, borderwidth, x, y, w, h, writing_mode):
def begin_div(self, color, borderwidth, x, y, w, h, writing_mode=False):
self._fontstack.append(self._font)
self._font = None
self.write('<div style="position:absolute; border: %s %dpx solid; writing-mode:%s; '
@ -288,6 +288,13 @@ class HTMLConverter(PDFConverter):
x*self.scale, (self._yoffset-y)*self.scale,
w*self.scale, h*self.scale))
return
def end_div(self, color):
if self._font is not None:
self.write('</span>')
self._font = self._fontstack.pop()
self.write('</div>')
return
def put_text(self, text, fontname, fontsize):
font = (fontname, fontsize)
@ -304,13 +311,6 @@ class HTMLConverter(PDFConverter):
self.write('<br>')
return
def end_textbox(self, color):
if self._font is not None:
self.write('</span>')
self._font = self._fontstack.pop()
self.write('</div>')
return
def receive_layout(self, ltpage):
def show_group(item):
if isinstance(item, LTTextGroup):
@ -334,9 +334,10 @@ class HTMLConverter(PDFConverter):
elif isinstance(item, LTCurve):
self.place_border('curve', 1, item)
elif isinstance(item, LTFigure):
self.place_border('figure', 1, item)
self.begin_div('figure', 1, item.x0, item.y1, item.width, item.height)
for child in item:
render(child)
self.end_div('figure')
elif isinstance(item, LTImage):
self.place_image(item, 1, item.x0, item.y1, item.width, item.height)
else:
@ -360,11 +361,11 @@ class HTMLConverter(PDFConverter):
if self.layoutmode != 'loose':
self.put_newline()
elif isinstance(item, LTTextBox):
self.begin_textbox('textbox', 1, item.x0, item.y1, item.width, item.height,
item.get_writing_mode())
self.begin_div('textbox', 1, item.x0, item.y1, item.width, item.height,
item.get_writing_mode())
for child in item:
render(child)
self.end_textbox('textbox')
self.end_div('textbox')
elif isinstance(item, LTChar):
self.put_text(item.get_text(), item.fontname, item.size)
elif isinstance(item, LTText):