def parse(self, page_html):
"""Get story metadata from given HTML."""
soup = BeautifulSoup(page_html, "html.parser")
title = FanfictionNetParser._get_title(soup)
if not title:
return ParseResult.failure("Could not find story title")
author = FanfictionNetParser._get_author(soup)
if not author:
return ParseResult.failure("Could not find author name")
summary = FanfictionNetParser._get_summary(soup)
if not summary:
return ParseResult.failure("Could not find summary")
universes = self._get_universes(soup)
if not universes:
return ParseResult.failure("Could not find universes")
# TODO: Handle "misc"?
return ParseResult.success(
title=title,
author=author,
summary=summary,
universes=universes)
def parse(self, page_contents):
"""Parse the html in page_contents for story information."""
soup = BeautifulSoup(page_contents, "html.parser")
title_tags = soup.select("li.work > div.header > h4.heading > a")
title = title_tags[0].string
author_tags = soup.select(
"li.work > div.header > h4.heading > a[rel=\"author\"]")
author = author_tags[0].string
summary_tags = soup.select("li.work > blockquote.summary > p")
summary = summary_tags[0].string
universes_tags = soup.select(
"li.work > div.header > h5.fandoms > a")
# TODO: Handle crossovers better
universes = frozenset([t.string for t in universes_tags])
return ParseResult.success(
title=title,
author=author,
summary=summary,
universes=universes)
