Follow 'Next Thread →' links

[paperdoorknob] / glowfic.py

diff --git a/glowfic.py b/glowfic.py
index 81a5342c2621d434dd320eb2104fb98d8eb34841..94fbd34bcfa00c4041d4fe74c5796775c162ca60 100644 (file)
--- a/glowfic.py
+++ b/glowfic.py
@@ -5,11 +5,11 @@
 # Free Software Foundation, version 3.
 
 
 # Free Software Foundation, version 3.
 
 

-from dataclasses import dataclass
+import dataclasses

 import itertools
 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
 
 from bs4 import BeautifulSoup
 from bs4.element import Tag


@@ -19,6 +19,10 @@ from spec import Spec
 from texify import Texifier
 
 
 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)
 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)))
 
 
     return urlunparse(u._replace(query=urlencode(qs)))
 
 

-@dataclass(frozen=True)
+@dataclasses.dataclass(frozen=True)

 class Chunk:
     icon: str | None
     character: Tag | None
 class Chunk:
     icon: str | None
     character: Tag | None


@@ -63,7 +67,7 @@ class Thread:
                 for a in c.findChildren('a'):
                     if 'Next Post' in a.text and 'href' in a.attrs and isinstance(
                             a.attrs['href'], str):
                 for a in c.findChildren('a'):
                     if 'Next Post' in a.text and 'href' in a.attrs and isinstance(
                             a.attrs['href'], str):

-                        return a.attrs['href']
+                        return urljoin(spec.url, a.attrs['href'])

             return None
 
         spec.log('Fetching HTML...\r')
             return None
 
         spec.log('Fetching HTML...\r')


@@ -73,6 +77,7 @@ class Thread:
         self._next_thread = find_next_thread(
             BeautifulSoup(spec.htmlfilter(html), 'html.parser'))
         self._dom = BeautifulSoup(spec.htmlfilter(flat_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")
 
     def title(self) -> str | None:
         span = self._dom.findChild("span", id="post-title")


@@ -98,6 +103,23 @@ class Thread:
 
         return itertools.chain([text()], the_replies())
 
 
         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 / num_chunks
+            self._spec.log(
+                f'Processing {title} {i} 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:
 
 
 def makeChunk(chunk_dom: Tag, image_store: ImageStore) -> Chunk: