Begin parsing glowfic html

[paperdoorknob] / paperdoorknob.py

diff --git a/paperdoorknob.py b/paperdoorknob.py
index bb8bdd1ae38a660b3a6f90aa3d5aa317505beee3..b88c02d73e64a604763ad5c8ca8785055496d53f 100644 (file)
--- a/paperdoorknob.py
+++ b/paperdoorknob.py
@@ -8,11 +8,24 @@
 from argparse import ArgumentParser
 import os.path
 from bs4 import BeautifulSoup
+from bs4.element import Tag
 import requests
 import requests_cache
 from xdg_base_dirs import xdg_cache_home
 
 
+class Post:
+    def __init__(self, html: BeautifulSoup) -> None:
+        self._html = html
+
+    def text(self) -> Tag:
+        body = self._html.body
+        assert body
+        text = body.find_next("div", class_="post-post")
+        assert isinstance(text, Tag)
+        return text
+
+
 def command_line_parser() -> ArgumentParser:
     parser = ArgumentParser(prog='paperdoorknob', description='Print glowfic')
     parser.add_argument(
@@ -37,7 +50,8 @@ def fetch(url: str, session: requests.Session, timeout: int) -> BeautifulSoup:
 def main() -> None:
     args = command_line_parser().parse_args()
     with requests_cache.CachedSession(args.cache_path, cache_control=True) as session:
-        fetch(args.url, session, args.timeout)
+        html = fetch(args.url, session, args.timeout)
+        Post(html)
 
 
 if __name__ == '__main__':