class Wikiparser(SGMLParser):
def __init__(self, url, verbose=0):
"Initialise an object, passing 'verbose' to the superclass."
SGMLParser.__init__(self, verbose)
self.hyperlinks = []
self.url = url
self.pdf = PDFWriter(self.url.split("/")[-1] +".pdf",595, 842)
header = Header(text_align = pango.ALIGN_CENTER)
#TODO Alignment not working.
header.set_text(self.url)
self.pdf.set_header(header)
h1= Text(self.url.split("/")[-1],font="Dyuthi",font_size=32)
self.pdf.add_h1(h1)
h2= Text(self.url,font="Rachan",font_size=16)
self.pdf.add_h2(h2)
footer = Footer(text_align = pango.ALIGN_CENTER)
footer.set_text("wiki2pdf")
self.pdf.set_footer(footer)
self.pdf.page_break()
def reset(self):
SGMLParser.reset(self)
self.images = []
#TODO Alignment not working.
self.h1 = False
self.h2 = False
self.li = False
self.p = False
self.a = False
self.ul = False
self.ol = False
self.span = False
self.buffer = None
def handle_data(self,data):
if data.strip() == "": return
if self.p or self.h1 or self.h2 or self.a or self.span:
if self.buffer!=None:
self.buffer+= data
def start_img(self, attrs):
src = [value for key, value in attrs if key=='src']
if src:
self.images.extend(src)
def start_h1(self, attrs):
self.h1=True
self.buffer=""
def end_h1(self):
self.h1=False
h1= Text(self.buffer,font="Dyuthi",font_size=16)
self.pdf.add_h1(h1)
self.buffer = None
def start_h2(self, attrs):
self.h2=True
self.buffer=""
def end_h2(self):
self.h2=False
if self.buffer and self.buffer.strip()>"":
h2= Text(self.buffer,font="Rachana",font_size=14)
self.pdf.add_h2(h2)
self.buffer = None
def start_li(self, attrs):
self.li=True
self.buffer=""
def end_li(self):
self.li=False
if self.buffer and self.buffer.strip()>"":
if self.ul:
li= Text("• "+self.buffer,font_size=10)
else:
li= Text(self.buffer,font_size=10)
self.pdf.add_li(li)
self.buffer = None
def start_a(self, attrs):
self.a = True
def end_a(self):
self.a = False
def start_ol(self,attrs):
self.ol=True
def end_ol(self):
self.ol=False
def start_ul(self,attrs):
self.ul=True
def end_ul(self):
self.ul=False
def start_span(self, attrs):
self.span=True
if self.buffer==None:
self.buffer=""
def end_span(self):
self.buffer+=" "
self.span=False
def start_p(self,attrs):
self.p=True
self.buffer=""
def end_p(self) :
self.p=False
para = Paragraph(text=self.buffer, font="Rachana",font_size=10,)
para.set_justify(True)
para.language = "ml_IN"
para.set_hyphenate(True)
self.pdf.add_paragraph(para)
self.buffer = None
def set_header(self,text):
self.header = text
def parse(self):
opener = urllib2.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
infile = opener.open(self.url)
page = infile.read()
page = cleanup(page)
"Parse the given string 's'."
self.feed(page)
self.close()
import pango
if __name__=="__main__":
pdf = PDFWriter("output.pdf",595, 842)
header = Header(text_align = pango.ALIGN_CENTER)
#TODO Alignment not working.
header.set_text("test header")
pdf.set_header(header)
footer = Footer(text_align = pango.ALIGN_CENTER)
footer.set_text("test footer")
#TODO Alignment not working.
pdf.set_footer(footer)
h1= Text("Samples",font_size=16)
pdf.add_h1(h1)
h2= Text("Malayalam",font_size=14)
pdf.add_h2(h2)
para_file_malayalam=open("malayalam.txt")
#image = Image(image_file="Four_Sons_of_Dasaratha.png")
#pdf.add_image(image)
while True:
para_content = para_file_malayalam.readline()
if para_content ==None or para_content=="" : break
para = Paragraph(text=para_content, font="Rachana")
pdf.add_paragraph(para)
h2= Text("Hindi",font_size=14, font="Rachana")
pdf.add_h2(h2)
para_file_hindi=open("hindi.txt")
while True:
para_content = para_file_hindi.readline()
if para_content ==None or para_content=="" : break
class Wikiparser(SGMLParser):
def reset(self):
SGMLParser.reset(self)
self.images = []
#TODO make the output file configurable- take it from command line
self.pdf = PDFWriter("output.pdf",595, 842)
header = Header(text_align = pango.ALIGN_CENTER)
#TODO Alignment not working.
header.set_text("A wikipedia article")
self.pdf.set_header(header)
footer = Footer(text_align = pango.ALIGN_CENTER)
footer.set_text("wiki2pdf")
#TODO Alignment not working.
self.pdf.set_footer(footer)
self.h1 = False
self.h2 = False
self.li = False
self.p = False
self.a = False
self.ul = False
self.ol = False
self.span = False
self.buffer = None
def handle_data(self,data):
if data.strip() == "": return
if self.p or self.h1 or self.h2 or self.a or self.span:
if self.buffer!=None:
self.buffer+= data
def start_img(self, attrs):
src = [value for key, value in attrs if key=='src']
if src:
self.images.extend(src)
def start_h1(self, attrs):
self.h1=True
self.buffer=""
def end_h1(self):
self.h1=False
h1= Text(self.buffer,font_size=16)
self.pdf.add_h1(h1)
self.buffer = None
def start_h2(self, attrs):
self.h2=True
self.buffer=""
def end_h2(self):
self.h2=False
if self.buffer and self.buffer.strip()>"":
h2= Text(self.buffer,font_size=14)
self.pdf.add_h2(h2)
self.buffer = None
def start_li(self, attrs):
self.li=True
self.buffer=""
def end_li(self):
self.li=False
if self.buffer and self.buffer.strip()>"":
if self.ul:
li= Text("• "+self.buffer,font_size=10)
else:
li= Text(self.buffer,font_size=10)
self.pdf.add_li(li)
self.buffer = None
def start_a(self, attrs):
self.a = True
def end_a(self):
self.a = False
def start_ol(self,attrs):
self.ol=True
def end_ol(self):
self.ol=False
def start_ul(self,attrs):
self.ul=True
def end_ul(self):
self.ul=False
def start_span(self, attrs):
self.span=True
if self.buffer==None:
self.buffer=""
def end_span(self):
self.buffer+=" "
self.span=False
def start_p(self,attrs):
self.p=True
self.buffer=""
def end_p(self) :
self.p=False
para = Paragraph(text=self.buffer, font="Rachana",font_size=10,)
para.set_justify(True)
self.pdf.add_paragraph(para)
self.buffer = None
