import re
target_file = "D:\CLIENTS\Random House\_CONVERSIONS\howbrit\New/final.epub"
image_output_dir = "D:\CLIENTS\Random House\_CONVERSIONS\howbrit\New/bakedcaptions"
font_size = 20
fontdir = "C:/Windows/Fonts/"
italicfont = "Bitter-Italic.otf"
regularfont = "Bitter-Regular.otf"
fontcolor = "#36250b"
default_x = 600
default_y = 800
data = []
with epub.epubFile(target_file) as pew:
# pew.info.findIDreferences(r"(page[0-9]*)")
imagefinder = re.compile(
'<div class="image">[\s]*<img alt="" class="image-fix"( height="[0-9]*")? src="(.*?)"( width="[0-9]*")? />[\s]*<p class="caption">(.*?)</p>[\s]*</div>'
)
for spine_item in pew.info.opf.spine:
contents = spine_item.read()
for match in re.finditer(imagefinder, contents):
proto_data = {
"src": None,
"caption": None,
"location": spine_item.opfRelLoc,
"item": None,
"match": None,
"x": None,
"y": None,
#!/usr/bin/python import epub import os test = epub.epubFile(os.path.join(os.path.dirname(__file__), "test_files/sample_file.epub")) #test = epub.epubFile(os.path.join(os.path.dirname(__file__), "test_files/sample_file.epub")) #get opf location test #print test.info._getOPFLocation() #contents test #for item in test.info.contents: # print item.info() #contents test2 #print test.info.contents.opfIdDir #print test.info.opf.contents.opfIdDir #manifest test #for item in test.info.opf.manifest: # print item.info() #spine test #for item in test.info.opf.spine: # print item.opfRelLoc #random test 1 #item = test.info.opf.manifest[1] #print item.info()
import re
target_file = "D:\CLIENTS\Random House\_CONVERSIONS\howbrit\New/final.epub"
image_output_dir = "D:\CLIENTS\Random House\_CONVERSIONS\howbrit\New/bakedcaptions"
font_size = 20
fontdir = "C:/Windows/Fonts/"
italicfont = "Bitter-Italic.otf"
regularfont = "Bitter-Regular.otf"
fontcolor = '#36250b'
default_x = 600
default_y = 800
data = []
with epub.epubFile(target_file) as pew:
#pew.info.findIDreferences(r"(page[0-9]*)")
imagefinder = re.compile(
"<div class=\"image\">[\s]*<img alt=\"\" class=\"image-fix\"( height=\"[0-9]*\")? src=\"(.*?)\"( width=\"[0-9]*\")? />[\s]*<p class=\"caption\">(.*?)</p>[\s]*</div>"
)
for spine_item in pew.info.opf.spine:
contents = spine_item.read()
for match in re.finditer(imagefinder, contents):
proto_data = {
"src": None,
"caption": None,
"location": spine_item.opfRelLoc,
"item": None,
"match": None,
"x": None,
"y": None,
