def imdb_direct_info(imdb_id):
print imdb_id
try:
html = urllib2.urlopen('http://www.imdb.com/title/'+imdb_id+'/').read()
except urllib2.HTTPError as e:
print e
return
html = re.sub(r'&#x(\w+);', r'%\1', html)
try:
html = unicode(html, 'utf-8')
except UnicodeDecodeError as e:
print "UnicodeDecodeError (%s) in %s" % (e, m)
return
html = urllib2.unquote(html)
xml = html2xml.translate(html)
page = xmlquery.parse_xml(xml)
info = page.queryone('#overview-top')
if not info: return
name = str(info.queryone('h1.header').children[0])
print name
year = info.queryone('h1.header>span>a')
if year: year = int(year.text)
print year
genres = map(lambda x: x.text, info.query('.infobar>a[href^="/genre/"]'))
print genres
rating = str(info.queryone('span[class="rating-rating"]').children[0])
if rating == '-': rating = 0
else: rating = float(rating)
print rating
votes = int(re.sub(',', '', info.queryone('a[href="ratings"]').text.split()[0]))
print votes
if len(info.query('p')) > 1:
short_plot = info.query('p')[1].text.splitlines()[0]
else:
short_plot = None
print short_plot
people = {}
for p_type in info.query('div.txt-block'):
p_type_text = p_type.queryone('h4.inline').text[:-1]
people[p_type_text] = []
for p in p_type.query('a[href^="/name/"]'):
people[p_type_text].append((p.text, p.attributes['href']))
print people
return
raise NotImplementedError()
(name, year) = re.search('<meta name="title" content="(.*?)\s\((\d{4})(?:/[IVX]+)?\)(?:\s\(T?V\))?">', html).group(1, 2)
m = re.search('<a href="ratings" class="tn15more">(\d+(?:,\d+)?) votes</a>', html)
if m: mvotes = int(re.sub(',', '', m.group(1)))
else: mvotes = 0
print name, year, mvotes
import xmlquery
xml = xmlquery.parse_xml("<a><b /></a>")
c = xml.query("*")
#c[1].name = "banana"
for n in c:
print n.name