def get(self):
url = self.request.get("url")
meta = {}
fetcheddata = urlfetch.fetch(url, deadline=10)
if fetcheddata.status_code == 200:
# parse the data to get the basic information out.
html = fetcheddata.content
# get the data
titleMatch = re.search(title, html, flags=re.IGNORECASE)
if titleMatch:
meta["name"] = titleMatch.group(
1) # only consider the first title
# get the data
imageMatch = re.search(image, html, flags=re.IGNORECASE)
if imageMatch:
meta["image"] = "http:" + imageMatch.group(1)
else:
self.response.status_code = fetcheddata.status_code
self.response.headers['Content-Type'] = "application/json"
self.response.out.write(simplejson2.dumps(meta, ensure_ascii=False))
def get(self):
url = self.request.get("url")
meta = {}
fetcheddata = urlfetch.fetch(url, deadline = 10)
meta["web_url"] = fetcheddata.final_url or url
meta["urls"] = [meta["web_url"]]
urlInfo = urlparse(meta["web_url"])
baseUrl = urlInfo.scheme + "://" + urlInfo.netloc + "/"
if fetcheddata.status_code == 200:
# parse the data to get the basic information out.
html = fetcheddata.content
# get the data
titleMatch = re.search(title, html, flags=re.IGNORECASE)
if titleMatch:
meta["name"] = titleMatch.group(1) # only consider the first title
descriptionMatch = re.search(description, html, flags=re.IGNORECASE)
if descriptionMatch:
meta["description"] = descriptionMatch.group(3)[0:132]
# parse the fav icons
meta["icons"] = dict([parseFavIcon(baseUrl, m)
for m in re.finditer(favicon, html, flags=re.IGNORECASE)
if m is not None])
# if "16" not in meta["icons"]:
# meta["icons"]["16"] = meta["web_url"] + "/favicon.ico"
#
# else:
self.response.status_code = fetcheddata.status_code
self.response.headers['Content-Type'] = "application/json"
self.response.out.write(simplejson2.dumps(meta, ensure_ascii=False))
def get(self):
url = self.request.get("url")
meta = {}
fetcheddata = urlfetch.fetch(url, deadline = 10)
if fetcheddata.status_code == 200:
# parse the data to get the basic information out.
html = fetcheddata.content
# get the data
titleMatch = re.search(title, html, flags=re.IGNORECASE)
if titleMatch:
meta["name"] = titleMatch.group(1) # only consider the first title
# get the data
imageMatch = re.search(image, html, flags=re.IGNORECASE)
if imageMatch:
meta["image"] = "http:" + imageMatch.group(1)
else:
self.response.status_code = fetcheddata.status_code
self.response.headers['Content-Type'] = "application/json"
self.response.out.write(simplejson2.dumps(meta, ensure_ascii=False))
