mirrors/pferd
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2025-07-12 22:22:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

"Fix" mypy errors

Browse Source 
Thank you mypy, very cool. These types make things *so much better*.
They don't just complicate everything and don't really help because they
can not detect that an element queried by a tag is no navigable
string...
This commit is contained in:
I-Al-Istannen
2025-02-12 22:41:43 +01:00
parent 16a2dd5b15
commit bd9d7efe64
8 changed files with 224 additions and 204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
PFERD/crawl/ilias/ilias_html_cleaner.py
View File

@ -1,3 +1,5 @@
from typing import cast
from bs4 import BeautifulSoup, Comment, Tag
_STYLE_TAG_CONTENT = """
@ -70,18 +72,18 @@ def insert_base_markup(soup: BeautifulSoup) -> BeautifulSoup:
def clean(soup: BeautifulSoup) -> BeautifulSoup:
for block in soup.find_all(class_=lambda x: x in _ARTICLE_WORTHY_CLASSES):
for block in cast(list[Tag], soup.find_all(class_=lambda x: x in _ARTICLE_WORTHY_CLASSES)):
block.name = "article"
for block in soup.find_all("h3"):
for block in cast(list[Tag], soup.find_all("h3")):
block.name = "div"
for block in soup.find_all("h1"):
for block in cast(list[Tag], soup.find_all("h1")):
block.name = "h3"
for block in soup.find_all(class_="ilc_va_ihcap_VAccordIHeadCap"):
for block in cast(list[Tag], soup.find_all(class_="ilc_va_ihcap_VAccordIHeadCap")):
block.name = "h3"
block["class"] += ["accordion-head"]
block["class"] += ["accordion-head"] # type: ignore
for dummy in soup.select(".ilc_text_block_Standard.ilc_Paragraph"):
children = list(dummy.children)
@ -97,7 +99,7 @@ def clean(soup: BeautifulSoup) -> BeautifulSoup:
if figure := video.find_parent("figure"):
figure.decompose()
for hrule_imposter in soup.find_all(class_="ilc_section_Separator"):
for hrule_imposter in cast(list[Tag], soup.find_all(class_="ilc_section_Separator")):
hrule_imposter.insert(0, soup.new_tag("hr"))
return soup