Merge cherry-picked commits from #33 (#43)

* update: component classifier functions * add: banner component parser * fix: return model as dict, require pydantic * fix: nonetype has no attrs; ignore if no img * fix: filter empty rso component * update: modularized component classifier * Bump to 0.3.2 * Replace dummy package bs4 with official name * Add function to load external html files * update: removed load_serp, see load_html in ws.webutils --------- Co-authored-by: wanLo <[email protected]>
gitronald · Nov 14, 2023 · 8243c12 · 8243c12
1 parent f9692d9
commit 8243c12
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/WebSearcher/searchers.py b/WebSearcher/searchers.py
@@ -189,7 +189,7 @@ def save_serp(self, save_dir='.', append_to=''):
         """Save SERP to file
 
         Args:
-            save_dir (str, optional): Save results as `save_dir/{serp_id}.json`
+            save_dir (str, optional): Save results as `save_dir/{serp_id}.html`
             append_to (str, optional): Append results to this file path
         """
         assert self.html, "Must conduct a search first"

diff --git a/setup.py b/setup.py
@@ -27,6 +27,6 @@ def get_readme_descriptions(fp='README.md', s='#', stop_at=2):
     long_description=long_description,
     long_description_content_type='text/markdown',
     packages=setuptools.find_packages(),
-    install_requires=['requests','lxml','bs4','tldextract','brotli', 'pydantic'],
+    install_requires=['requests','lxml','beautifulsoup4','tldextract','brotli','pydantic'],
     python_requires='>=3.6'
 )