scrape-yuanyuan/utils/linkutils.py

"""Utility functions for handling links."""
import csv
from typing import List, NamedTuple, TextIO


class Link(NamedTuple):
    """A type for links - contains its url and date."""

    url: str
    date: str


def dump_links(links: List[Link], f: TextIO):
    """Dump links to a file in csv format."""
    writer = csv.writer(f)
    writer.writerow(["index", "link", "date"])
    for i, link in enumerate(links):
        writer.writerow([i, link[0], link[1]])


def read_links(f: TextIO) -> List[Link]:
    """Read links from a csv format."""
    reader = csv.reader(f)
    next(reader)  # Skip the header
    return [Link(link[1], link[2]) for link in reader]


def absolutize_link(link: str, page_base: str) -> str:
    """Ensure we have an absolute url."""
    if link.startswith("./"):
        link = page_base + link[2:]
    return link