def __fetch_linkedin_c_data(self):
if not self.domain.linkedin_c:
return
try:
data = fetch(self.domain.linkedin_c, True)
except:
logger.debug('Can\'t fetch LinkedIn data for {}'.format(self.domain.linkedin_c))
return
try:
tree = html.fromstring(data)
except:
logger.debug('Can\'t create LXML tree for {}'.format(self.domain.linkedin_c))
return
self.domain.linkedin_c_short_desc = get_from_list_by_index(tree.xpath(data, '//*[@id="body"]/div[2]/div[1]/div[1]/div/p[1]/text()'), 0)
self.domain.linkedin_c_followers = get_from_list_by_index(tree.xpath(data, '//*[@id="biz-follow-mod"]/div/div/p/strong/text()'), 0)
self.domain.linkedin_c_spe = get_from_list_by_index(tree.xpath(data, '//*[@id="content"]/div[2]/div[2]/div/p/text()'), 0)
self.domain.linkedin_c_website = get_from_list_by_index(tree.xpath(data, '//*[@id="content"]/div[1]/div[2]/ul/li[1]/p/a/text()'), 0)
self.domain.linkedin_c_industry = get_from_list_by_index(tree.xpath(data, '//*[@id="content"]/div[1]/div[2]/ul/li[2]/p/text()'), 0)
self.domain.linkedin_c_address = get_from_list_by_index(tree.xpath(data, '//*[@id="content"]/div[1]/div[2]/ul/li[4]/p/span[1]/text()'), 0)
self.domain.linkedin_c_comp_size = get_from_list_by_index(tree.xpath(data, '//*[@id="content"]/div[1]/div[2]/ul/li[5]/p/text()'), 0)
self.domain.linkedin_c_founded = get_from_list_by_index(tree.xpath(data, '//*[@id="content"]/div[2]/div[2]/ul/li[6]/p/text()'), 0)
def __init__(self, name, proxy_always=False, links_content=('about', 'contact', 'info'), emails_black_list=tuple(), *args, **kwargs):
super().__init__(name)
if not isinstance(links_content, tuple):
raise TypeError('Invalid links content argument type. Can\'t create Cache Walker instance.')
if not isinstance(emails_black_list, tuple):
raise TypeError('Invalid emails black list argument type. Can\'t create Cache Walker instance.')
self.proxy_always = proxy_always
self.pages = list()
root_url = 'http://{}'.format(self.domain.get_name())
try:
home_page_data = fetch(root_url, self.proxy_always)
except:
logger.error('Can\'t fetch home page for \'{}\'. Domain is not active'.format(self.domain.get_name()))
return
self.domain.active = True
self.pages.append(home_page_data)
links = self.get_similar_links(home_page_data, root_url, links_content)
for l in links:
try:
self.pages.append(fetch(l, self.proxy_always))
except:
logger.warning('Can\'t fetch data from {}.'.format(l))
continue
self.domain.gapps = self.check_gapps(self.domain.get_name())
self.domain.emails = set(self.parse_by_regex('([\w\-]+@(?:(?!example)[\w\-]+\.)+[a-z]+)')) - set(emails_black_list)
self.domain.facebook = get_from_list_by_index(self.parse_by_regex(FACEBOOK_LINKS_PATTERN), 0)
self.domain.twitter = get_from_list_by_index(self.parse_by_regex(TWITTER_LINKS_PATTERN), 0)
self.domain.linkedin_c = get_from_list_by_index(self.parse_by_regex(LINKEDIN_COMPANY_LINKS_PATTERN), 0)
self.domain.linkedin_g = get_from_list_by_index(self.parse_by_regex(LINKEDIN_GROUP_LINKS_PATTERN), 0)
self.domain.linkedin_u = get_from_list_by_index(self.parse_by_regex(LINKEDIN_USER_LINKS_PATTERN), 0)
self.__fetch_linkedin_c_data()
def check_gapps(name):
if not isinstance(name, str):
raise ValueError('Invalid name argument type.')
url = 'https://www.google.com/a/{}/ServiceLogin'.format(name)
try:
data = fetch(url)
except:
return
try:
tree = html.fromstring(data)
result = (tree.xpath('//title/text()') or (None,))[0]
print(result)
except:
return
if result == 'Sign in - Google Accounts':
return True
return False
