def _parse(self, course: NavigableString) -> ParseType:
"""Parses course to get its link & icon url, title, description
counts and stores.
:course: BeautifulSoup Object"""
info = {
"link": "",
"icon": "",
"title": "",
"description": "",
"counts": {}
}
info["link"] = course.a["href"]
info["icon"] = course.a.img["src"]
description: NavigableString = course.a.div
info["title"] = description.div.get_text()
info["description"] = description.p.get_text()
counts: NavigableString = course.find("div", {"class": "courseCounts"})
counts_data: ResultSet = counts.find_all("li")
for data in counts_data:
name: str = data.span.get_text().lower()
val: str = data.find("p").get_text()
info["counts"][name] = int(val.replace(",", ""))
return info
def _parse_details(self, code: NavigableString) -> ParseType:
"""Parses a codeContainer and extracts all the info."""
# Format of details ->
# {votes: 1184, answers: 24077, post_link: <PostLink> title: <Title>,
# tags: [<Tags>, ...], author_name: <AuthorName>, author_link: <Link>,
# data_date: <DateTime>, avatar_link: <Link>}
details: ParseType = {}
post_stats: NavigableString = code.find("div", {"class": "postStats"})
post_stats_children = list(post_stats.children)
details["votes"] = post_stats_children[1].p.string
# Note the spelling of <a class='postAnsewers'.
details["answers"] = post_stats_children[3].p.string
post_details: NavigableString = code.find("div",
{"class": "postDetails"})
details["post_link"] = post_details.p.a["href"]
details["title"] = post_details.p.a.string
tags_wrapper: NavigableString = list(post_details.children)[3]
tags: ResultSet = tags_wrapper.find_all("span")
tag_list: List[str] = []
for tag in tags:
tag_list.append(tag.string)
details["tags"] = tag_list
author_details: NavigableString = code.find("div",
{"class": "authorDetails"})
details["author_name"] = author_details.div.a.string
details["author_link"] = author_details.div.a["href"]
details["data_date"] = author_details.p["data-date"]
details["avatar_link"] = list(author_details.children)[3].img["src"]
return details
def unwrap_ul(li: element.NavigableString) -> WebToonChapter:
link = li.find('a')['href']
pretty_name = li.find('img')['alt']
chapter = WebToonChapter.from_url(link, pretty_name)
return chapter