def process_item(processed_items, index): lecture = Lecture() lecture.month = processed_items[0] lecture.day = processed_items[1] title = '' for position in range(2, index): title += "{} ".format(str(processed_items[position]).lower()) lecture.title = capwords(title.strip()) speaker = '' for position in range(index + 1, len(processed_items)): speaker += "{} ".format(str(processed_items[position]).strip('.').lower().title()) lecture.speaker = speaker.strip() return lecture
def processLecture(self,lectureTr): columns = lectureTr.findAll("td") serierNumber = columns[0] date = columns[3] title = columns[4] try: serierInt = int(serierNumber.text) except ValueError: return if "Re:" in title.text: return else : lecture = Lecture() url = title.find('a') lecture.link = url.attrs['href'] try: dateAndTitle = (title.text.split('[')[1]).split("]") if len(dateAndTitle[0]) != 5: return lecture.date = dateAndTitle[0] lecture.title = dateAndTitle[1] self.lectures.append(lecture) except IndexError: return