Hi.
I try to create a metadata download plugin for a Hungarian online shop called libri.hu.
First I have made a python script that downloads the metadata and print it in the console.
The I try to convert it to a plugin for Calibre, but I stucked.
In debug mode I can see it prints out the data for the book but at the end of the run of the plugin I get an error message:
Code:
Traceback (most recent call last):
File "threading.py", line 525, in __bootstrap_inner
File "D:\Calibre Libary\calibre\src\calibre\gui2\dialogs\fetch_metadata.py", l
ine 38, in run
File "D:\Calibre Libary\calibre\src\calibre\ebooks\metadata\fetch.py", line 32
0, in search
File "D:\Calibre Libary\calibre\src\calibre\ebooks\metadata\fetch.py", line 28
7, in filter_metadata_results
AttributeError: 'str' object has no attribute 'publisher'
I'm new in python and I have just basic programing skills.
My code is now just a basic scratch version, and I try to do fine tuning and make some error handling in the future.
The metadata it scrapes mostly contains special Hungarian characters.
Here is my plugins code:
Code:
# -*- coding: utf-8 -*-
import lxml, sys
import lxml.html as lh
#import traceback
from calibre import browser
from calibre.customize import Plugin
from calibre.ebooks.metadata.fetch import MetadataSource
from calibre.ebooks.metadata import MetaInformation
def get_social_metadata(title, authors, publisher, isbn):
print '4'
mi = MetaInformation(title, authors)
SEARCH_URL = "http://www.libri.hu/reszletes_kereso"
print '5'
br = browser()
br.open(SEARCH_URL)
br.select_form(name = "detailed_search_form")
br['cim'] = title
br['szerzo'] = authors
# br['isbn'] = isbn
search_page = br.submit()
book_page = br.follow_link(url_regex='konyv', nr=0)
print search_page.geturl()
print book_page.geturl()
doc = lh.parse(book_page)
book_title = ''.join(doc.xpath('//*[@id="book"]/div/h1/text()')).replace("\t",'').replace("\n",'')
print book_title
mi.title = book_title
book_author = ''.join(doc.xpath('//*[@id="book"]//*[@class="authors"]//text()')).replace("\t",'').replace("\n",'')
print book_author
mi.authors = book_author
book_property = doc.xpath('//*[@class="props"]/text()')
book_property = [text for text in book_property if text != '\r\n\t\t\t\t\t\r\n\t\t\t' and text != '\r\n\t\t\t\t' and text != '\r\n\t\t\t\t\r\n\t\t\t\t\t\r\n\t\t\t\t' and text != ' ' and text != ': ']
book_publish_date = ''.join(book_property[6]).replace(" ",'').replace("\t",'').replace("\n",'')
print book_publish_date
mi.pubdate = book_publish_date
book_publisher = ''.join(doc.xpath('//*[@class="props"]/a/text()'))
print book_publisher
mi.publisher = book_publisher
#mi.series = series[0].strip()
book_comments = ''.join(doc.xpath('//*[@id="tab_content_lead"]//text()')).replace("\t",'').replace("\n",'')
print book_comments
mi.comments = book_comments
book_isbn = ''.join(book_property[5]).replace(" ",'').replace("\t",'').replace("\n",'')
print book_isbn
mi.isbn=book_isbn
return mi
class LibraryThing(MetadataSource):
author = 'Csaba Hoffer'
metadata_type = 'basic'
name = 'Libri_Hu'
description = _('Downloads metadata from Libri.hu')
version = (1, 0, 0)
supported_platforms = ['windows', 'osx', 'linux']
print '1'
def fetch(self):
print '2'
try:
self.results = get_social_metadata(self.title, self.book_author, self.publisher, self.isbn)
print '8'
#print self.results
print '9'
except Exception, e:
print '6'
self.exception = e
self.tb = traceback.format_exc()
def main(args=sys.argv):
print get_social_metadata(None, None, None, None)
return 0
if __name__ == '__main__':
sys.exit(main())
Please, if anyone have some hint for me what could be the problem share it with me.
Thanks!