def __init__(self, url):
self.url = url
try:
self.html = urlfetch.fetch(url).content
except urlfetch_errors.InvalidURLError:
return
self.soup = BeautifulSoup(self.html)
self.populate_me_links()
def extractLogo(self, html):
soup = BeautifulSoup(html)
img = soup.find('img', id='logo')
div = soup.find('div', id='logo')
description = ''
if img:
pic = img['src']
if 'title' in img: description = img['title']
elif div:
pic = re.search(r'(?<=url\()\S+(?=\))', str(div)).group(0)
else:
msg = 'Cronjob: Logos: could not find IMG or DIV tag with logo id!'
logging.error(msg)
print msg
return False
#pic = pic.decode(charset)
return [pic, description]
class Page:
url = ""
html = ""
soup = None
hcards = []
me_links = []
def __init__(self, url):
self.url = url
try:
self.html = urlfetch.fetch(url).content
except urlfetch_errors.InvalidURLError:
return
self.soup = BeautifulSoup(self.html)
self.populate_me_links()
def populate_me_links(self):
self.me_links = [
urlparse.urljoin(self.url, tag["href"]) for tag in self.soup.findAll(attrs={"rel": "me"}) if tag.get("href")
]