`src/conrad/crawlers/denver_post.py`

24 lines
"""Denver Post (Conrad's paper 1950-1964). Archive is PAYWALLED (newspapers.com / NewsBank). Not crawled;
source registered and coverage computed from other repositories' attributions."""
from __future__ import annotations

from .base import Crawler


class DenverPost(Crawler):
    source_id = "denver_post"
    name = "Denver Post archive (newspapers.com / NewsBank)"
    repository = "Denver Post"
    url = "https://denverpost.newspapers.com/"
    classification = "PAYWALLED"
    access_notes = "Denver Post 1950-1964 pages via subscription databases or Denver Public Library microfilm."

    def crawl(self) -> None:
        n = self.conn.execute("SELECT COUNT(*) FROM cartoons WHERE publication='Denver Post' AND granularity='item'"
                              ).fetchone()[0]
        self.status = "not_attempted"
        self.notes.append(f"paywalled — not crawled; {n} item records elsewhere are attributed to the Denver Post")


CRAWLER = DenverPost