Termania script

termania.py

#!/usr/bin/env python3
"""Termania api

Usage:
	termania [options] [QUERY [QUERY ...]]

Options:
   -h --help         Show this screen.
   --version         Show version.
"""

from urllib.request import urlopen
from urllib.parse import urlencode
import re

from pyquery import PyQuery as pq
from docopt import docopt

SEARCH_URL = 'http://www.termania.net/iskanje?{}'

LINE_QUERY = '{}: '
LINE_NAME=' * [{}] {}'
LINE_OPT='\n        {} '
NL = '\n'

def search(query):
	print(LINE_QUERY.format(query))
	result = pq(url=SEARCH_URL.format(urlencode({ 'Query': query })),
				opener=lambda url, **kw: urlopen(url).read())

	for li in result("#results .center .left.listing li"):
		lang = li.find('img').attrib.get('title')
		name = li.find('h4')
		print(LINE_NAME.format(lang, name.text_content()), end='')
		
		has_images = False
		for elt in li.find('p'):
			if elt.tag == 'img':
				has_images = True
				break
		i = 1
		p_content = li.find('p').text_content()
		no_strong = True
		for p in li.find('p'):
			if p.tag == 'img':
				lang = p.attrib.get('title')
				if not lang: continue
				print (LINE_OPT.format(lang), end='')
			elif p.tag == 'strong':
				content = p.text_content()
				if not content: continue
				no_strong = False
				if not has_images:
					print (LINE_OPT.format(str(i) + '.'), end='')
				if re.match(r'^\d+\. .+', content):
					print (LINE_OPT.format(content), end='')
				else:
					print (content + ' ', end='')
				i += 1
		if no_strong:
			print (p_content, end='')
		print(NL)
			
		
if __name__ == '__main__':
	arguments = docopt(__doc__, version='0.1')
	queries = arguments.get('QUERY')
	if queries:
		search(' '.join(queries))
	else:
		import subprocess
		p = subprocess.Popen(['xclip', '-o'], stdout=subprocess.PIPE)
		out, err = p.communicate()
		if not err:
			search(out.decode('utf8'))