zdic.net query draft code

# import re
import urllib
import sys
import getopt
from lxml import etree, html

# from util import hook


# @hook.command('u')
# @hook.command
def zdic(inp):
    '''.zd/.zdic <Chinese word in characters> -- looks up <word> on zdic.net/cd/'''

    url = 'http://www.zdic.net/sousuo'

    params = {'lb_a': 'hp', 'lb_b': 'mh', 'lb_c': 'mh', 'tp': 'tp1', 'q': inp}
    page = post_get(url, params)

#    page = http.get_html(url, term=inp)

#    words = page.xpath("//td[@class='word']")
#    defs = page.xpath("//div[@class='definition']")
    defs = page.xpath("//p[@class='zdct1']")
    pinyin = page.xpath("//span[@class='dicpy']")

    if not defs:
        return 'no definitions found'

#    out = defs[1].text_content().strip() + ': ' + ' '.join(
#            defs[0].text_content().split())

    out = [None]*2
    out[0] = defs[1].text_content().strip() + defs[2].text_content().strip()
    out[1] = defs[3].text_content().strip() + defs[4].text_content().strip()
    
    for c in out:
        if len(c) > 400:
            c = c[:c.rfind(' ', 0, 400)] + '...'

    return out


def post_get(url, params):
    f = urllib.urlopen(url, urllib.urlencode(params))
    import pdb; pdb.set_trace()
    text = f.read()
    outfile(text + '\n\n' + params['q'])
    return html.fromstring(text)


def main():
    # parse command line options
    try:
        opts, args = getopt.getopt(sys.argv[1:], "h", ["help"])
    except getopt.error, msg:
        print msg
        print "for help use --help"
        sys.exit(2)
    # process options
    for o, a in opts:
        if o in ("-h", "--help"):
            print __doc__
            sys.exit(0)
    # process arguments
    for arg in args:
        print zdic(arg) # process() is defined elsewhere


def outfile(text):
    of = open('zdret.txt', 'w')
    of.write(text)
    of.close()
    

if __name__ == "__main__":
    main()