def _anything_1(self,*args): tosearch = [] for arg in args: tosearch.append(str(arg)) self.input = ' '.join(tosearch) if hasattr(self, 'howmany'): howmany = self.howmany dbgmsg = "%s%d%s%s" % ("getting ", self.howmany, " results about: ", self.input) self._outlet(4, dbgmsg) for tweet in Twitter().search(self.input, cached=False)[:howmany]: author = encode_utf8(plaintext(tweet.author)) date = encode_utf8(plaintext(tweet.date)) description = encode_utf8(plaintext(tweet.description)) self._outlet(1, description) self._outlet(2, author) self._outlet(3, date)
def extract_tvseries(dom): ''' Extract a list of highest ranking TV series from DOM (of IMDB page). Each TV series entry should contain the following fields: - TV Title - Ranking - Genres (comma separated if more than one) - Actors/actresses (comma separated if more than one) - Runtime (only a number!) ''' tvseries = [] # iterates over top 50 IMBD tv series for tvserie in dom.by_tag("td.title")[:50]: tvserie_array = [] genres_array = [] actors_array = [] # tv serie title is encoded and added to tv serie array title = tvserie("a")[0].content tvserie_array.append(encode_utf8(title)) # tv serie ranking is encoded and added to tv serie array ranking = tvserie("span.value")[0].content tvserie_array.append(encode_utf8(ranking)) # tv serie genres are added to tv serie array for genres in tvserie("span.genre a"): # genre is encoded and added to genres array genres_array.append(encode_utf8(genres.content)) # seprates genres with commas genres = COMMA.join(genres_array) tvserie_array.append(genres) # tv serie actors are added to tv serie array for actors in tvserie("span.credit a"): # actor is encoded and added to actors array actors_array.append(encode_utf8(actors.content)) # seprates actors with commas actors = COMMA.join(actors_array) tvserie_array.append(actors) # tv serie runtime is encoded and stripped to numbers runtime = encode_utf8(tvserie("span.runtime")[0].content) runtime = runtime.rstrip(' mins.') tvserie_array.append(runtime) tvseries.append(tvserie_array) return tvseries
def _anything_1(self,*args): #default vars varservice = 'imap.gmail.com' varport = 993 varsecure = True varfolder = 'inbox' varquery = '' varfield = 'subject' howmany = 1 if hasattr(self, 'service'): varservice = self.service if hasattr(self, 'port'): varport = self.port if hasattr(self, 'folder'): varfolder = self.folder if hasattr(self, 'search'): varquery = self.search if hasattr(self, 'howmany'): howmany = self.howmany if hasattr(self, 'username') and hasattr(self, 'passw'): self.input = str(args[0]) mail = Mail(self.username, self.passw, service=varservice, port=varport) if self.input == "search": mailres = getattr(mail,varfolder).search(varquery, field=varfield) for amail in mailres[:howmany]: m = getattr(mail,varfolder).read(amail) self._outlet(2, encode_utf8(plaintext(m.author))) self._outlet(3, encode_utf8(plaintext(m.subject))) self._outlet(4, encode_utf8(plaintext(m.body))) self._outlet(5, m.attachments) elif self.input == "getf": print mail.folders for folder in mail.folders.keys(): self._outlet(1, folder) else: self._outlet(6, "you need to insert username and password inlets")
def test_encode_utf8(self): # Assert Python bytestring. for s in self.strings: self.assertTrue(isinstance(web.encode_utf8(s), str)) print "pattern.web.encode_utf8()"
def test_encode_utf8(self): # Assert Python bytestring. for s in self.strings: self.assertTrue(isinstance(web.encode_utf8(s), str)) print "pattern.web.encode_utf8()"
def _anything_1(self,*args): #default vars varstart=1 varcount=10 varsort='relevancy' varsize='medium' download=False outpath=tempfile.gettempdir() tosearch = [] for arg in args: tosearch.append(str(arg)) self.input = ' '.join(tosearch) if hasattr(self, 'start'): varstart = self.start if hasattr(self, 'count'): varcount = self.count if hasattr(self, 'sort'): varsort = self.sort if hasattr(self, 'size'): varsize = self.size if hasattr(self, 'download'): download = self.download if hasattr(self, 'outpath'): outpath = os.path.abspath(self.outpath) dbgmsg = "%s%d%s%d%s%s%s%s%s%s%s%s%s%s" % ("start:", varstart, " count:", varcount, " sort:", varsort, " size:", varsize, " search:", self.input, " download:", download, " output path:", outpath) self._outlet(5, dbgmsg) engine = Flickr(license=None) results = engine.search(self.input, start=varstart, count=varcount, sort=varsort, size=varsize, cached=False) if (download): now = datetime.datetime.now() timenow = "%s%s%s" % (self.input, "_", now.strftime('%Y%m%d-%H%M')) pathdir = os.path.join(outpath, timenow) if not os.path.isdir(pathdir): os.mkdir(pathdir) output = "%s%s" % ("created: ", str(pathdir)) self._outlet(5, output) for img in results: author = encode_utf8(plaintext(img.author)) description = encode_utf8(img.description) url = encode_utf8(img.url) self._outlet(1, description) self._outlet(2, author) self._outlet(3, url) if (download): if url != "None": data = img.download() filename = img.url.rsplit("/",1)[1] pathfile = os.path.join(pathdir, filename) f = open(pathfile, "w") f.write(data) f.close() output = "%s%s" % ("downloaded: ", str(pathfile)) self._outlet(5, output) if (download): self._outlet(4, str(pathdir))