X-Git-Url: http://git.scottworley.com/paperdoorknob/blobdiff_plain/19ed28f37b59e480cebe8f122e07ce18ce536db8..fc2aaa75baff15d201153efeeda0c4c5898e4822:/glowfic.py?ds=inline diff --git a/glowfic.py b/glowfic.py index 5ffaac3..9d863c8 100644 --- a/glowfic.py +++ b/glowfic.py @@ -7,7 +7,7 @@ from dataclasses import dataclass import itertools -from urllib.parse import parse_qsl, urlencode, urlparse, urlunparse +from urllib.parse import parse_qsl, urlencode, urljoin, urlparse, urlunparse from typing import Iterable @@ -58,10 +58,21 @@ class Chunk: class Thread: def __init__(self, spec: Spec) -> None: + def find_next_thread(dom: BeautifulSoup) -> str | None: + for c in dom.findChildren('div', class_='post-navheader'): + for a in c.findChildren('a'): + if 'Next Post' in a.text and 'href' in a.attrs and isinstance( + a.attrs['href'], str): + return urljoin(spec.url, a.attrs['href']) + return None + spec.log('Fetching HTML...\r') - html = spec.fetcher.fetch(flatURL(spec.url)) + html = spec.fetcher.fetch(spec.url) + flat_html = spec.fetcher.fetch(flatURL(spec.url)) spec.log('Parsing HTML...\r') - self._dom = BeautifulSoup(spec.htmlfilter(html), 'html.parser') + self._next_thread = find_next_thread( + BeautifulSoup(spec.htmlfilter(html), 'html.parser')) + self._dom = BeautifulSoup(spec.htmlfilter(flat_html), 'html.parser') def title(self) -> str | None: span = self._dom.findChild("span", id="post-title") @@ -69,6 +80,9 @@ class Thread: return None return span.text.strip() + def next_thread(self) -> str | None: + return self._next_thread + def chunkDOMs(self) -> Iterable[Tag]: def text() -> Tag: body = self._dom.body