def find_info(self, url):
# get video id
match = re.match(URL_REGEX_PREFIX + 'vimeo\.com/(\S*)', url)
if match is None:
return
self.video_id = match.group(1)
logger.info("Found vimeo video: " + self.video_id)
json_url = "http://vimeo.com/api/v2/video/{0}.json".format(self.video_id)
json_content = download_page(json_url).decode("utf-8")
json_data = json.loads(json_content)
json_data = json_data[0]
raw_title = json_data["title"]
title = self.msg_formats.bold(self.msg_formats.red(raw_title))
secs = int(json_data["duration"])
duration = self.msg_formats.green(str(int(secs / 60)) + "m " + str(secs % 60) + "s")
message = "{0} :: {1}".format(title, duration)
return (message, raw_title)
def search_site(self, url, resource_dict):
"""Downloads the URL's content, searches for the paths and patterns
and builds a message out of the matched data.
Arguments: resource_dict contains the paths, patterns and additional data for
the url.
"""
if self.sitedata is None:
return
# retrieve content
try:
content = download_page(url).decode(WEB_ENCODING, "replace")
except:
return
if content is None:
return
message = None
title = None
def info_xpath():
# try to find info using xpath
root = lxml.html.fromstring(content)
items = root.xpath(info["xpath"])
logger.debug("using xpath: " + info["xpath"])
if items is not None and len(items) >= 1:
return items[0]
else:
return None
def info_regex():
# try to find info using a regex pattern
logger.debug("using regex: " + info["pattern"])
match = re.search(info["pattern"], content)
if match is None:
logger.warning(
"Could not find info! (match == None) with pattern: " +
info["pattern"])
return None
if match.groups() is None:
logger.warning("match.groups() was None")
return None
if len(match.groups()) <= 0:
logger.warning("Found match but no groups")
return None
return match.group(1)
for info in resource_dict["patterns"]:
if not "pattern" in info and not "xpath" in info:
logger.error(
"siteinfo entry does not contain a path or pattern!")
break
infodata = None
# try regex first because it seems to be faster
if "pattern" in info:
infodata = info_regex()
# try xpath if there was no pattern or regex was unsuccessful
if infodata is None and "xpath" in info:
infodata = info_xpath()
if infodata is None:
logger.warning("infodata was None!")
break
logger.debug("\ninfodata:\n")
logger.debug(infodata)
if infodata is None or infodata == "":
continue
logger.info("found info data: " + infodata)
infodata = unescape(infodata)
infodata = escape(infodata)
infodata = infodata.strip()
if title is None:
title = infodata
color = REST_COLOR
style = REST_STYLE
if message is None:
message = ""
color = FIRST_COLOR
style = FIRST_STYLE
message += self.msg_formats.get(
style, self.msg_formats.get(color, infodata))
if info != resource_dict["patterns"][-1]:
message += " " + self.sitedata["separator"] + " "
# cut last separator if there is one
sep = self.sitedata["separator"]
if message is not None and message.strip()[-len(sep):] == sep:
message = message.strip()[:-len(sep)].strip()
return message, title
def search_site(self, url, resource_dict):
"""Downloads the URL's content, searches for the paths and patterns
and builds a message out of the matched data.
Arguments: resource_dict contains the paths, patterns and additional data for
the url.
"""
if self.sitedata is None:
return
# retrieve content
try:
content = download_page(url).decode(WEB_ENCODING, "replace")
except:
return
if content is None:
return
message = None
title = None
def info_xpath():
# try to find info using xpath
root = lxml.html.fromstring(content)
items = root.xpath(info["xpath"])
logger.debug("using xpath: " + info["xpath"])
if items is not None and len(items) >= 1:
return items[0]
else:
return None
def info_regex():
# try to find info using a regex pattern
logger.debug("using regex: " + info["pattern"])
match = re.search(info["pattern"], content)
if match is None:
logger.warning("Could not find info! (match == None) with pattern: " + info["pattern"])
return None
if match.groups() is None:
logger.warning("match.groups() was None")
return None
if len(match.groups()) <= 0:
logger.warning("Found match but no groups")
return None
return match.group(1)
for info in resource_dict["patterns"]:
if not "pattern" in info and not "xpath" in info:
logger.error("siteinfo entry does not contain a path or pattern!")
break
infodata = None
# try regex first because it seems to be faster
if "pattern" in info:
infodata = info_regex()
# try xpath if there was no pattern or regex was unsuccessful
if infodata is None and "xpath" in info:
infodata = info_xpath()
if infodata is None:
logger.warning("infodata was None!")
break
logger.debug("\ninfodata:\n")
logger.debug(infodata)
if infodata is None or infodata == "":
continue
logger.info("found info data: " + infodata)
infodata = unescape(infodata)
infodata = escape(infodata)
infodata = infodata.strip()
if title is None:
title = infodata
color = REST_COLOR
style = REST_STYLE
if message is None:
message = ""
color = FIRST_COLOR
style = FIRST_STYLE
message += self.msg_formats.get(style, self.msg_formats.get(color, infodata))
if info != resource_dict["patterns"][-1]:
message += " " + self.sitedata["separator"] + " "
# cut last separator if there is one
sep = self.sitedata["separator"]
if message is not None and message.strip()[-len(sep) :] == sep:
message = message.strip()[: -len(sep)].strip()
return message, title
