def detect(self, message):
"""
Given a 'message' detects its language.
Returns Language object.
"""
message = quote_plus(message)
real_url = LanguageDetector.detect_url % {'message': message}
try:
detection = self.browser.get_page(real_url)
data = json.loads(detection)
if data['responseStatus'] != 200:
raise DetectionError("Failed detecting language: %s" %
data['responseDetails'])
rd = data['responseData']
return Language(rd['language'], rd['confidence'], rd['isReliable'])
except BrowserError(e):
raise DetectionError(
"Failed detecting language (getting %s failed): %s" %
(e.url, e.error))
except ValueError(e):
raise DetectionErrro(
"Failed detecting language (json failed): %s" % e.message)
except KeyError(e):
raise DetectionError(
"Failed detecting language, response didn't contain the necessary data"
)
return None
def _get_results_page(self, set_type):
if set_type == LARGE_SET:
url = GoogleSets.URL_LARGE
else:
url = GoogleSets.URL_SMALL
safe_items = [urllib.quote_plus(i) for i in self.items]
blank_items = 5 - len(safe_items)
if blank_items > 0:
safe_items += ['']*blank_items
safe_url = url % tuple(safe_items)
try:
page = self.browser.get_page(safe_url)
except BrowserError(e):
raise GSError("Failed getting %s: %s" % (e.url, e.error))
return BeautifulSoup(page)
def translate(self, message, lang_to='en', lang_from=''):
"""
Given a 'message' translate it from 'lang_from' to 'lang_to'.
If 'lang_from' is empty, auto-detects the language.
Returns the translated message.
"""
if lang_to not in _languages:
raise TranslationError("Language %s is not supported as lang_to." %
lang_to)
if lang_from not in _languages and lang_from != '':
raise TranslationError(
"Language %s is not supported as lang_from." % lang_from)
message = quote_plus(message)
real_url = Translator.translate_url % {
'message': message,
'from': lang_from,
'to': lang_to
}
try:
translation = self.browser.get_page(real_url)
data = json.loads(translation)
if data['responseStatus'] != 200:
raise TranslationError("Failed translating: %s" %
data['responseDetails'])
return data['responseData']['translatedText']
except BrowserError(e):
raise TranslationError(
"Failed translating (getting %s failed): %s" %
(e.url, e.error))
except ValueError(e):
raise TranslationError("Failed translating (json failed): %s" %
e.message)
except KeyError(e):
raise TranslationError(
"Failed translating, response didn't contain the translation")
return None
def _get_results_page(self):
if not self.older:
url = RealtimeSearch.SEARCH_URL
safe_url = [
url % {
'query': urllib.quote_plus(self.query),
'tld': self._tld,
'lang': self._lang
}
]
safe_url = "".join(safe_url)
self.older = safe_url
else:
safe_url = self.older
self._last_search_url = safe_url
try:
page = self.browser.get_page(safe_url)
except BrowserError(e):
raise RealtimeSearchError("Failed getting %s: %s" %
(e.url, e.error))
return BeautifulSoup(page)
def _get_results_page(self):
if self._page == 0:
if self._results_per_page == 10:
url = GoogleSearch.SEARCH_URL_0
else:
url = GoogleSearch.SEARCH_URL_1
else:
if self._results_per_page == 10:
url = GoogleSearch.NEXT_PAGE_0
else:
url = GoogleSearch.NEXT_PAGE_1
safe_url = [
url % {
'query': urllib.quote_plus(self.query),
'start': self._page * self._results_per_page,
'num': self._results_per_page,
'tld': self._tld,
'lang': self._lang
}
]
# possibly extend url with optional properties
if self._first_indexed_in_previous:
safe_url.extend(["&as_qdr=", self._first_indexed_in_previous])
if self._filetype:
safe_url.extend(["&as_filetype=", self._filetype])
safe_url = "".join(safe_url)
self._last_search_url = safe_url
try:
page = self.browser.get_page(safe_url)
except BrowserError(e):
raise SearchError("Failed getting %s: %s" % (e.url, e.error))
return BeautifulSoup(page)
def _get_results_page(self):
if self._page == 0:
if self._results_per_page == 10:
url = SponsoredLinks.SEARCH_URL_0
else:
url = SponsoredLinks.SEARCH_URL_1
else:
if self._results_per_page == 10:
url = SponsoredLinks.NEXT_PAGE_0
else:
url = SponsoredLinks.NEXT_PAGE_1
safe_url = url % {
'query': urllib.quote_plus(self.query),
'start': self._page * self._results_per_page,
'num': self._results_per_page
}
try:
page = self.browser.get_page(safe_url)
except BrowserError(e):
raise SLError("Failed getting %s: %s" % (e.url, e.error))
return BeautifulSoup(page)