def parse_chapters(soup):
results = soup.find_all('h1')
raw_chapters = [
data.Chapter(
text=result.text,
soup_index=get_soup_index(soup, result))
for result in results]
chapters = merge_adjacent_chapter_items(raw_chapters)
clean_chapter_text(chapters)
return chapters
def parse_chapters(soup):
results = soup.find_all('h1')
raw_chapters = [
data.Chapter(text=result.text, soup_index=get_soup_index(soup, result))
for result in results
]
chapters = merge_adjacent_chapter_items(raw_chapters)
clean_chapter_text(chapters)
chapters = [
chapter for chapter in chapters if not should_be_excluded(chapter)
]
return chapters
def merge_two(a, b):
if (a.text in b.text) or (b.text in a.text):
text = a.text
else:
text = a.text + ' ' + b.text
return data.Chapter(text=text, soup_index=a.soup_index)