35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
from bs4 import BeautifulSoup
|
|
|
|
|
|
def get_names(page, config_data: dict) -> list[tuple[str, str]]:
|
|
base = config_data["base"]
|
|
html_content: str = page.content()
|
|
|
|
# Parse the HTML content using BeautifulSoup
|
|
soup = BeautifulSoup(html_content, "html.parser")
|
|
|
|
# Find the table with class "nb list"
|
|
table = soup.find("table", {"class": "nb list"})
|
|
|
|
assert table is not None
|
|
|
|
# Extract rows from the table body (tbody)
|
|
tbody = table.find("tbody")
|
|
rows = tbody.find_all("tr", {"class": "tbdata"})
|
|
|
|
# Extract the first and second column from all rows
|
|
list_entries: list[tuple[str, str]] = []
|
|
|
|
for row in rows:
|
|
cells = row.find_all("td")
|
|
|
|
if len(cells) > 1:
|
|
link_tag = cells[0].find("a")
|
|
assert link_tag is not None
|
|
entry_name: str = cells[0].text.strip().title().replace(" ", "_")
|
|
entry_link: str = f"{base}{link_tag.get("href")}"
|
|
entry_id: str = cells[1].text.strip()
|
|
entry_path: str = f"{entry_id}_{entry_name}"
|
|
list_entries.append((entry_path, entry_link))
|
|
|
|
return list_entries
|