Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixed "No chapters found" error in two sources #2161

Merged
merged 4 commits into from
Oct 12, 2023
Merged

Fixed "No chapters found" error in two sources #2161

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0bbae76
Fixed source: Free Web Novel
CryZFix Oct 9, 2023
0ba49c0
Remove not used imports
CryZFix Oct 9, 2023
3842039
Added mirror of site
CryZFix Oct 9, 2023
65e55f4
Fixed source: "WanderingInn"
CryZFix Oct 11, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 4 additions & 17 deletions sources/en/f/freewebnovel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,6 @@
# -*- coding: utf-8 -*-
import unicodedata

from concurrent.futures import Future
from typing import List

from bs4 import BeautifulSoup, Tag

from lncrawl.models import Chapter, SearchResult
Expand All @@ -12,7 +9,7 @@


class FreeWebNovelCrawler(SearchableSoupTemplate, ChapterOnlySoupTemplate):
base_url = ["https://freewebnovel.com/", "https://bednovel.com/", "https://innread.com/"]
base_url = ["https://freewebnovel.com/", "https://bednovel.com/", "https://innread.com/", "https://innnovel.com/"]

def initialize(self) -> None:
self.init_executor(ratelimit=2)
Expand Down Expand Up @@ -80,19 +77,9 @@ def parse_authors(self, soup: BeautifulSoup):
yield a.text.strip()

def select_chapter_tags(self, soup: BeautifulSoup):
pages = soup.select("#indexselect > option")

futures: List[Future] = []
for page in pages:
url = self.absolute_url(page["value"])
f = self.executor.submit(self.get_soup, url)
futures.append(f)

self.resolve_futures(futures, desc="TOC", unit="page")
for i, future in enumerate(futures):
assert future.done(), f"Failed to get page {i + 1}"
soup = future.result()
yield from soup.select(".m-newest2 li > a")
chapters = soup.select("#idData")
for chapter in chapters:
yield from chapter.select("li > a")

def parse_chapter_item(self, tag: Tag, id: int) -> Chapter:
return Chapter(
Expand Down
27 changes: 14 additions & 13 deletions sources/en/w/wanderinginn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,21 +33,22 @@ def read_novel_info(self):

# Extract volume-wise chapter entries
# Stops external links being selected as chapters
chapters = soup.select('div.entry-content a[href*="wanderinginn"]')

for a in chapters:
chap_id = len(self.chapters) + 1
vol_id = 1 + len(self.chapters) // 100
volumes = soup.select("div#table-of-contents div[id*='vol']")
for volume in volumes:
chapters = volume.select('div#table-of-contents .chapter-entry a[href*="wanderinginn"]')
vol_id = 1 + len(self.volumes)
if len(self.volumes) < vol_id:
self.volumes.append({"id": vol_id})
self.chapters.append(
{
"id": chap_id,
"volume": vol_id,
"url": self.absolute_url(a["href"]),
"title": a.text.strip() or ("Chapter %d" % chap_id),
}
)
for a in chapters:
chap_id = len(self.chapters) + 1
self.chapters.append(
{
"id": chap_id,
"volume": vol_id,
"url": self.absolute_url(a["href"]),
"title": a.text.strip() or ("Chapter %d" % chap_id),
}
)

def download_chapter_body(self, chapter):
soup = self.get_soup(chapter["url"])
Expand Down