Handle Unicode characters ≈ and ◁

[paperdoorknob] / glowfic.py

diff --git a/glowfic.py b/glowfic.py
index 5ffaac31921e360961967832ad090074e5cd2aaa..275c163ca3389fbcc40f781a1821c920b8843495 100644 (file)
--- a/glowfic.py
+++ b/glowfic.py
@@ -5,11 +5,11 @@
 # Free Software Foundation, version 3.
 
 
-from dataclasses import dataclass
+import dataclasses
 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
+from typing import Any, Iterable
 
 from bs4 import BeautifulSoup
 from bs4.element import Tag
@@ -19,6 +19,10 @@ from spec import Spec
 from texify import Texifier
 
 
+def ilen(it: Iterable[Any]) -> int:
+    return sum(1 for _ in it)
+
+
 def _removeViewFromURL(url: str) -> str:
     u = urlparse(url)
     old_qs = parse_qsl(u.query)
@@ -36,7 +40,7 @@ def flatURL(url: str) -> str:
     return urlunparse(u._replace(query=urlencode(qs)))
 
 
-@dataclass(frozen=True)
+@dataclasses.dataclass(frozen=True)
 class Chunk:
     icon: str | None
     character: Tag | None
@@ -58,10 +62,22 @@ 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')
+        self._spec = spec
 
     def title(self) -> str | None:
         span = self._dom.findChild("span", id="post-title")
@@ -69,6 +85,9 @@ 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
@@ -84,6 +103,23 @@ class Thread:
 
         return itertools.chain([text()], the_replies())
 
+    def emit(self) -> None:
+        self._spec.log('Counting chunks...\r')
+        num_chunks = ilen(self.chunkDOMs())
+        title = self.title() or "chunk"
+        for i, r in enumerate(self.chunkDOMs()):
+            percent = 100.0 * (i + 1) / num_chunks
+            self._spec.log(
+                f'Processing {title} {i+1} of {num_chunks} ({percent:.1f}%)\r')
+            self._spec.domfilter(r)
+            chunk = makeChunk(r, self._spec.images)
+            self._spec.texout.write(
+                self._spec.texfilter(renderChunk(self._spec.texifier, chunk)))
+        self._spec.log('')
+        next_url = self.next_thread()
+        if next_url is not None:
+            Thread(dataclasses.replace(self._spec, url=next_url)).emit()
+
 
 def makeChunk(chunk_dom: Tag, image_store: ImageStore) -> Chunk: