def fetch_chapter(chapter_prefix, chapter):
chapter_bsoup = get_soup(get_chapter_html(chapter_prefix, chapter))
chapter_title = get_chapter_title(chapter_bsoup)
chapter_content = get_chapter_content(chapter_bsoup)
return Chapter(no=chapter, title=chapter_title, content=chapter_content)
# novels = fetch_all_novel("http://www.truyenngan.com.vn/truyen-ngan.html")
# for novel in novels:
# # novel.print()
# for chapter in novel.chapters:
# chapter.print()
# # print("--------------------------------------------------------")
# chapter = fetch_chapter("http://truyenfull.vn/truyen-than-khong-thien-ha", 1)
# chapter.print()
# def db_save_novel(novel_id):
# def db_save_chapter(novel_id, title, content, chapter):
# html = get_html("http://truyenfull.vn/pham-nhan-tu-tien", 333)
# soup = get_soup(html)
# title = get_chapter_title(soup)
# content = get_content(soup)
# print(title)
# print(content)
# html = get_novel_html("http://truyenfull.vn/truyen-than-khong-thien-ha/")
# soup = get_soup(html)
# print(get_novel_genre(soup))
def fetch_all_novel(novel_list_url):
soup = get_soup(get_html(novel_list_url))
novels = []
all_story_group = soup.find_all("div", "wrap-carousel-cate")
for story_group_bsoup in all_story_group:
story_bsoups = story_group_bsoup.find("ul").find_all("li")
story_bsoup = story_bsoups[0]
detail_link = "http://www.truyenngan.com.vn/" + story_bsoup.find(
"div", "carousel-cate-img").a["href"]
detail = get_soup(get_html(detail_link))
image = story_bsoup.find("div", "carousel-cate-img").a.img["src"]
title = story_bsoup.find("div", "carousel-cate-title").a.get_text()
description = detail.find("strong").get_text()
novel = Novel(title, "", description, image, "Truyện ngắn")
novel.chapters = []
novels.append(novel)
no = 1
for story_bsoup in story_bsoups:
detail_link = "http://www.truyenngan.com.vn/" + story_bsoup.find(
"div", "carousel-cate-img").a["href"]
title = story_bsoup.find("div", "carousel-cate-title").a.get_text()
detail = get_soup(get_html(detail_link))
author = detail.find("div", "details-poster").a.strong.get_text()
content = str(detail.find("div", "maincontent"))
chapter = Chapter(no, title + " - " + author, content)
novel.chapters.append(chapter)
no += 1
return novels
def create_chapter(uid, name, mid):
from models import db
from models.user import User
from models.manga import Manga
from models.chapter import Chapter
# check user privilege
user = User.query.get(uid)
if not user.privilege.operate_chapter:
return 1
# check manga existence
manga = Manga.query.get(mid)
if manga is None:
return 2
# create chapter
new_chapter = Chapter(chapter_name=name, aff_mid=mid)
db.session.add(new_chapter)
db.session.commit()
update_chapter(new_chapter)
# create two default quests
quest1_code = create_quest(uid, "翻译", "TRANSLATION", False,
new_chapter.cid)
quest2_code = create_quest(uid,
"校对",
"PROOFREADING",
False,
new_chapter.cid,
isClosed=True)
quest3_code = create_quest(uid,
"嵌字",
"TYPESETTING",
False,
new_chapter.cid,
isClosed=True)
return 0
def __load_chapters(self, chapters_texts):
if self.language not in self.pipeline:
self.pipeline[self.language] = stanza.Pipeline(
**DocumentParser.PIPELINE_CFG, lang=self.language)
res = []
for chapter_text in chapters_texts:
title, text = chapter_text.split('\n', 1)
model = self.pipeline[self.language](text)
res.append(Chapter(model, title, self.language))
return res
def begin_new_chapter(self, chapter_number_str):
chapter_number = int(chapter_number_str)
if(self.current_chapter):
self.current_book.add_chapter(self.current_chapter)
self.current_chapter = Chapter(chapter_number)
def parse_chapter(self, text, title=None):
model = self.pipeline(text)
return Chapter(model, title if title else self.chapter_title,
self.lang)