Seanchas Rann na Feirste scraper pieces

import requests
from bs4 import BeautifulSoup
BASE='http://www.rannnafeirste.com'

class Page:
	def __init__(self, id, title):
		self.id = id
		self.title = title
		self.url = '{}/{}'.format(BASE, id)

	# TODO: stop trying to make fetch happen
	def _fetch_text(self):
		req = requests.get(self.url)
		if req.status_code != 200:
			raise Exception('Error fetching page ' + self.url)
		self.content = req.content
	def _soupynorman(self):
		self.soup = BeautifulSoup(self.content, 'html.parser')
	def _fetch_audio(self):
		audio_div = self.soup.find("div", class_='sqs-audio-embed')
		self.audio = audio_div["data-url"]
	def _fetch_fragments(self):
		for i in self.soup.find_all("div", class_='sqs-block-content'):
			children = list(i.children)
			if children[0].name == "h1":
				self.fragments = children
	## don't actually need this, because the title comes from the landing page
	def _fetch_title(self):
		if self.fragments[0].name == "h1":
			self.title = fragments[0].text
		else:
			raise Exception('Error reading title: ' + self.url)
	def _fetch_author(self):
		if len(self.fragments) > 2 and self.fragments[1].name == "h2":
			self.author = self.fragments[1].text
		else:
			raise Exception('Error reading author: ' + self.url)
	def _fetch_paragraphs(self):
		raw_paras = [n for n in self.fragments if n.name == "p"]
		for frag in raw_paras:
			for br in frag.find_all("br"):
				br.insert(0, '\n')
				br.unwrap()
		first = list(raw_paras[0].children)
		if len(first) == 1 and first[0].name == 'em':
				self.em_para = raw_paras[0].text.strip()
				del raw_paras[0]
		extent = len(raw_paras)
		counter = 0
		for i in raw_paras:
				if i.text.strip().startswith('Nóta') or i.text.strip().startswith('NÓTA') and extent > counter:
						extent = counter
				counter += 1
		filt = raw_paras[0:extent]
		self.paragraphs = [p.text for p in filt]
	def get_initials(self):
		fada = {
			'Á': 'A',
			'É': 'E',
			'Í': 'I',
			'Ó': 'O',
			'Ú': 'U'
		}
		def initial(s):
			if s == None or len(s) < 1:
				return ''
			else:
				return fada.get(s.upper()[0]) or s.upper()[0]
		try:
			return "".join([initial(i) for i in self.author.split(' ')])
		except:
			print('Author missing: did you run scrape()?')

	def _specifics(self):
		title = ['mo-bhaile-dchais', 'taiscidh-ghleann-domhain', 'banron-an-uaignis', 'non-an-r-agus-an-frog', 'seanchaithe-agus-fil-rann-na-feirste', 'an-ghaeltacht-bheo']
		titlele = ['liontar-duinn-an-cruiscin', 'oireachtas-na-ndise', 'fidilir-ghleann-fhinne']

		if self.id in title:
			self.paragraphs.insert(0, self.title)

		if self.id in titlele:
			second = self.em_para.replace(' a chum', '')
			self.paragraphs.insert(0, '{} le {}'.format(self.title, second))

	def scrape(self):
		self._fetch_text()
		self._soupynorman()
		self._fetch_audio()
		self._fetch_fragments()
		self._fetch_author()
		self._fetch_paragraphs()
		self._specifics()

foo = Page('deorai-an-oileain', 'Mo Bhaile')
foo.scrape()
foo.paragraphs

para = foo.fragments[4]

#one = para.contents[0]
for br in para.find_all("br"):
  br.insert(0, '\n')
  br.unwrap()

para.contents

raw_paras = [n for n in foo.fragments if n.name == "p"]
#raw_paras
first = list(raw_paras[0].children)
if len(first) == 1 and first[0].name == 'em':
  del raw_paras[0]
extent = len(raw_paras)
counter = 0
for i in raw_paras:
  print(i.text)
  if i.text.strip().startswith('Nóta') or i.text.strip().startswith('NÓTA') and extent > counter:
    extent = counter
  counter += 1
raw_paras[0:extent]
#counter