def set_profile(self, *args):
section = self.profile
for arg in args[:-2]:
try:
s = section[arg]
except KeyError:
s = section[arg] = ProfileNode(arg, arg.capitalize().replace('_', ' '), OrderedDict(), flags=ProfileNode.SECTION)
section = s.value
key = args[-2]
value = args[-1]
section[key] = ProfileNode(key, key.capitalize().replace('_', ' '), value)
def parse_profile(self, profile, consts):
if profile['online']:
self.status = Contact.STATUS_ONLINE
self.status_msg = u'online'
self.status_msg = u'since %s' % profile['last_cnx']
else:
self.status = Contact.STATUS_OFFLINE
self.status_msg = u'last connection %s' % profile['last_cnx']
self.summary = unicode(HTMLParser().unescape(
profile.get('announce', '').strip()))
if len(profile.get('shopping_list', '')) > 0:
self.summary += u'\n\nLooking for:\n%s' % HTMLParser().unescape(
profile['shopping_list'].strip())
for photo in profile['pics']:
self.set_photo(photo.split('/')[-1],
url=photo + '/full',
thumbnail_url=photo + '/small',
hidden=False)
self.profile = OrderedDict()
if 'sex' in profile:
for section, d in self.TABLE.items():
flags = ProfileNode.SECTION
if section.startswith('_'):
flags |= ProfileNode.HEAD
if (section.startswith('+') and int(profile['sex']) != 1) or \
(section.startswith('-') and int(profile['sex']) != 0):
continue
section = section.lstrip('_+-')
s = ProfileNode(section,
section.capitalize(),
OrderedDict(),
flags=flags)
for key, builder in d.items():
try:
value = builder.get_value(profile,
consts[int(profile['sex'])])
except KeyError:
pass
else:
s.value[key] = ProfileNode(
key,
key.capitalize().replace('_', ' '), value)
self.profile[section] = s
self._aum_profile = profile
def parse_profile(self, profile, consts):
if profile['online']:
self.status = Contact.STATUS_ONLINE
self.status_msg = u'online'
self.status_msg = u'since %s' % profile['last_cnx']
else:
self.status = Contact.STATUS_OFFLINE
self.status_msg = u'last connection %s' % profile['last_cnx']
self.summary = unicode(unescape(profile.get('announce', '').strip()))
if len(profile.get('shopping_list', '')) > 0:
self.summary += u'\n\nLooking for:\n%s' % unescape(profile['shopping_list'].strip())
for photo in profile['pics']:
self.set_photo(photo.split('/')[-1],
url=photo + '/full',
thumbnail_url=photo + '/small',
hidden=False)
self.profile = OrderedDict()
if 'sex' in profile:
for section, d in self.TABLE.iteritems():
flags = ProfileNode.SECTION
if section.startswith('_'):
flags |= ProfileNode.HEAD
if (section.startswith('+') and int(profile['sex']) != 1) or \
(section.startswith('-') and int(profile['sex']) != 0):
continue
section = section.lstrip('_+-')
s = ProfileNode(section, section.capitalize(), OrderedDict(), flags=flags)
for key, builder in d.iteritems():
try:
value = builder.get_value(profile, consts[int(profile['sex'])])
except KeyError:
pass
else:
s.value[key] = ProfileNode(key, key.capitalize().replace('_', ' '), value)
self.profile[section] = s
self._aum_profile = profile
def get_profile(self):
title = self.parser.select(self.document.getroot(), 'title', 1)
if title.text == 'OkCupid: Account Not Found':
return None
profile = {}
profile['id'] = unicode(title.text[len('OkCupid: '):])
profile['data'] = OrderedDict()
profile_p = self.parser.select(self.document.getroot(), "//div[@id='page_content']//p", method='xpath')
profile['data']['infos'] = ProfileNode('infos', u'Informations', OrderedDict(), flags=ProfileNode.SECTION)
info = {
'age' : unicode(profile_p[1].text.split(' / ')[0]),
'sex' : unicode(profile_p[1].text.split(' / ')[1]),
'orientation' : unicode(profile_p[1].text.split(' / ')[2]),
'relationship' : unicode(profile_p[1].text.split(' / ')[3]),
}
for key, val in info.iteritems():
profile['data']['infos'].value[key] = ProfileNode(key, key.capitalize(), val)
div_essays = self.parser.select(self.document.getroot(), "//div[@class='essay']", method='xpath')
h3_essays = self.parser.select(self.document.getroot(), "//div[@id='page_content']//h3", method='xpath')
essays = OrderedDict(zip(h3_essays, div_essays))
profile['data']['look_for'] = ProfileNode('look_for', u'Look for', OrderedDict(), flags=ProfileNode.SECTION)
profile['data']['details'] = ProfileNode('details', u'Details', OrderedDict(), flags=ProfileNode.SECTION)
profile['data']['essays'] = ProfileNode('essays', u'Essays', OrderedDict(), flags=ProfileNode.SECTION)
for label, val in essays.iteritems():
label = unicode(label.text).strip()
txt = self.parser.tocleanstring(val)
if 'looking for' in label:
for i, li in enumerate(val.xpath('.//li')):
profile['data']['look_for'].value['look_for_%s' % i] = ProfileNode('look_for_%s' % i, '', li.text.strip())
elif 'summary' in label and 'summary' not in profile:
profile['summary'] = txt
else:
key = label.replace(' ', '_')
profile['data']['essays'].value[key] = ProfileNode(key, label, txt)
details_div = self.parser.select(self.document.getroot(), "//div[@id='details']//li", method='xpath')
for elem in details_div:
label = unicode(elem.getchildren()[0].text.strip())
val = unicode(elem.getchildren()[1].text.strip())
key = label.lower().replace(' ', '_')
profile['data']['details'].value[key] = ProfileNode(key, label, val)
return profile
def get_profile(self):
title = self.parser.select(self.document.getroot(), 'title', 1)
if title.text == 'OkCupid: Account Not Found':
return None
profile = {}
profile['id'] = unicode(title.text[len('OkCupid: '):])
profile['data'] = OrderedDict()
profile_p = self.parser.select(self.document.getroot(), "//div[@id='page_content']//p", method='xpath')
profile['data']['infos'] = ProfileNode('infos', u'Informations', OrderedDict(), flags=ProfileNode.SECTION)
info = {
'age' : unicode(profile_p[1].text.split(' / ')[0]),
'sex' : unicode(profile_p[1].text.split(' / ')[1]),
'orientation' : unicode(profile_p[1].text.split(' / ')[2]),
'relationship' : unicode(profile_p[1].text.split(' / ')[3]),
}
for key, val in info.iteritems():
profile['data']['infos'].value[key] = ProfileNode(key, key.capitalize(), val)
div_essays = self.parser.select(self.document.getroot(), "//div[@class='essay']", method='xpath')
h3_essays = self.parser.select(self.document.getroot(), "//div[@id='page_content']//h3", method='xpath')
essays = dict(zip(h3_essays, div_essays))
profile['summary'] = unicode(div_essays[0].text.strip())
profile['data']['essays'] = ProfileNode('essays', u'Essays', OrderedDict(), flags=ProfileNode.SECTION)
for label, val in essays.iteritems():
label = unicode(label.text).strip()
val = unicode(val.text).strip()
key = label.replace(' ', '_')
profile['data']['essays'].value[key] = ProfileNode(key, label, val)
#profile['data']['look_for'].value['orientation'] = ProfileNode('orientation', 'Orientation', div_essays[9].getchildren()[0].getchildren()[0].text.strip())
#profile['data']['look_for'].value['location'] = ProfileNode('location', 'Location', div_essays[9].getchildren()[0].getchildren()[2].text.strip())
#profile['data']['look_for'].value['relationship'] = ProfileNode('relationship', 'Relationship', div_essays[9].getchildren()[0].getchildren()[3].text.strip())
#profile['data']['look_for'].value['what_for'] = ProfileNode('what_for', 'What for', div_essays[9].getchildren()[0].getchildren()[4].text.split('\n')[1].strip().split(', '))
#age = div_essays[9].getchildren()[0].getchildren()[1].text[5:].strip().split(u'–')
#profile['data']['look_for'].value['age_min'] = ProfileNode('age_min', 'Age min', int(age[0]))
#profile['data']['look_for'].value['age_max'] = ProfileNode('age_max', 'Age max', int(age[1]))
#div_essays = div_essays[1:-1]
#h3_essays = h3_essays[1:-1]
#for i, title in enumerate(h3_essays):
# profile['data']['essays'].value['essay_%i' % i] = ProfileNode('essay_%i' % i, title.text, div_essays[i].text.strip())
details_div = self.parser.select(self.document.getroot(), "//div[@id='details']//li", method='xpath')
profile['data']['details'] = ProfileNode('details', u'Details', OrderedDict(), flags=ProfileNode.SECTION)
for elem in details_div:
label = unicode(elem.getchildren()[0].text.strip())
val = unicode(elem.getchildren()[1].text.strip())
key = label.lower().replace(' ', '_')
profile['data']['details'].value[key] = ProfileNode(key, label, val)
return profile
def _set_profile(self, contact, key, value):
contact.profile[key] = ProfileNode(key, key.capitalize(), value)
def get_profile(self):
title = self.parser.select(self.document.getroot(), 'title', 1)
if title.text == 'OkCupid: Account Not Found':
return None
profile = {}
profile['id'] = unicode(title.text[len('OkCupid: '):])
profile['data'] = OrderedDict()
profile_p = self.parser.select(
self.document.getroot(),
"//div[@id='page_content']//div[contains(@class, 'basics')]//p",
method='xpath')
profile['data']['infos'] = ProfileNode('infos',
u'Informations',
OrderedDict(),
flags=ProfileNode.SECTION)
info = {
'age': profile_p[1].text.split(u'•', 1)[0].strip(),
'location': profile_p[1].text.split(u'•', 1)[1].strip(),
'sex': profile_p[2].text.strip(),
}
for key, val in info.iteritems():
profile['data']['infos'].value[key] = ProfileNode(
key, key.capitalize(), val)
div_essays = self.parser.select(self.document.getroot(),
"//div[@class='essay']",
method='xpath')
h3_essays = self.parser.select(self.document.getroot(),
"//div[@id='page_content']//h3",
method='xpath')
essays = OrderedDict(zip(h3_essays, div_essays))
profile['data']['look_for'] = ProfileNode('look_for',
u'Look for',
OrderedDict(),
flags=ProfileNode.SECTION)
profile['data']['details'] = ProfileNode('details',
u'Details',
OrderedDict(),
flags=ProfileNode.SECTION)
profile['data']['essays'] = ProfileNode('essays',
u'Essays',
OrderedDict(),
flags=ProfileNode.SECTION)
for label, val in essays.iteritems():
label = unicode(label.text).strip()
txt = self.parser.tocleanstring(val)
if 'looking for' in label:
for i, li in enumerate(val.xpath('.//li')):
profile['data']['look_for'].value['look_for_%s' %
i] = ProfileNode(
'look_for_%s' % i,
'', li.text.strip())
elif 'summary' in label and 'summary' not in profile:
profile['summary'] = txt
else:
key = label.replace(' ', '_')
profile['data']['essays'].value[key] = ProfileNode(
key, label, txt)
details_div = self.parser.select(self.document.getroot(),
"//div[@id='details']//li",
method='xpath')
for elem in details_div:
label = unicode(elem.getchildren()[0].text.strip())
val = unicode(elem.getchildren()[1].text.strip())
key = label.lower().replace(' ', '_')
profile['data']['details'].value[key] = ProfileNode(
key, label, val)
return profile
def get_profile(self):
title = self.parser.select(self.document.getroot(), 'title', 1)
if title.text == 'OkCupid: Account Not Found':
return None
profile = {}
profile['id'] = unicode(title.text[len('OkCupid: '):])
profile['data'] = OrderedDict()
profile_p = self.parser.select(self.document.getroot(),
"//div[@id='page_content']//p",
method='xpath')
profile['data']['infos'] = ProfileNode('infos',
u'Informations',
OrderedDict(),
flags=ProfileNode.SECTION)
info = {
'age': unicode(profile_p[1].text.split(' / ')[0]),
'sex': unicode(profile_p[1].text.split(' / ')[1]),
'orientation': unicode(profile_p[1].text.split(' / ')[2]),
'relationship': unicode(profile_p[1].text.split(' / ')[3]),
}
for key, val in info.iteritems():
profile['data']['infos'].value[key] = ProfileNode(
key, key.capitalize(), val)
div_essays = self.parser.select(self.document.getroot(),
"//div[@class='essay']",
method='xpath')
h3_essays = self.parser.select(self.document.getroot(),
"//div[@id='page_content']//h3",
method='xpath')
essays = dict(zip(h3_essays, div_essays))
profile['summary'] = unicode(div_essays[0].text.strip())
profile['data']['essays'] = ProfileNode('essays',
u'Essays',
OrderedDict(),
flags=ProfileNode.SECTION)
for label, val in essays.iteritems():
label = unicode(label.text).strip()
val = unicode(val.text).strip()
key = label.replace(' ', '_')
profile['data']['essays'].value[key] = ProfileNode(key, label, val)
#profile['data']['look_for'].value['orientation'] = ProfileNode('orientation', 'Orientation', div_essays[9].getchildren()[0].getchildren()[0].text.strip())
#profile['data']['look_for'].value['location'] = ProfileNode('location', 'Location', div_essays[9].getchildren()[0].getchildren()[2].text.strip())
#profile['data']['look_for'].value['relationship'] = ProfileNode('relationship', 'Relationship', div_essays[9].getchildren()[0].getchildren()[3].text.strip())
#profile['data']['look_for'].value['what_for'] = ProfileNode('what_for', 'What for', div_essays[9].getchildren()[0].getchildren()[4].text.split('\n')[1].strip().split(', '))
#age = div_essays[9].getchildren()[0].getchildren()[1].text[5:].strip().split(u'–')
#profile['data']['look_for'].value['age_min'] = ProfileNode('age_min', 'Age min', int(age[0]))
#profile['data']['look_for'].value['age_max'] = ProfileNode('age_max', 'Age max', int(age[1]))
#div_essays = div_essays[1:-1]
#h3_essays = h3_essays[1:-1]
#for i, title in enumerate(h3_essays):
# profile['data']['essays'].value['essay_%i' % i] = ProfileNode('essay_%i' % i, title.text, div_essays[i].text.strip())
details_div = self.parser.select(self.document.getroot(),
"//div[@id='details']//li",
method='xpath')
profile['data']['details'] = ProfileNode('details',
u'Details',
OrderedDict(),
flags=ProfileNode.SECTION)
for elem in details_div:
label = unicode(elem.getchildren()[0].text.strip())
val = unicode(elem.getchildren()[1].text.strip())
key = label.lower().replace(' ', '_')
profile['data']['details'].value[key] = ProfileNode(
key, label, val)
return profile