"""Unit tests for cores.search — HTTP + image extraction + UA."""
from __future__ import annotations
from cores.search import extract_image_urls_from_html, is_social_media_url, random_user_agent
class TestExtractImageUrls:
def test_extracts_img_src(self):
html = '
'
imgs = extract_image_urls_from_html(html, base_url="https://example.com/")
assert len(imgs) == 1
assert imgs[0]["url"] == "https://example.com/a.jpg"
assert imgs[0]["alt"] == "A"
def test_resolves_relative_urls(self):
html = '
'
imgs = extract_image_urls_from_html(html, base_url="https://example.com/page")
assert imgs[0]["url"] == "https://example.com/images/b.png"
def test_skips_data_uris(self):
html = '
'
imgs = extract_image_urls_from_html(html)
assert imgs == []
def test_skips_tiny_images(self):
html = '
'
imgs = extract_image_urls_from_html(html, min_size=50)
assert imgs == []
def test_max_images_limit(self):
html = "".join(f'
' for i in range(100))
imgs = extract_image_urls_from_html(html, max_images=10)
assert len(imgs) == 10
def test_handles_data_src(self):
html = '![]()
'
imgs = extract_image_urls_from_html(html, base_url="https://example.com/")
assert len(imgs) == 1
assert imgs[0]["url"] == "https://example.com/lazy.jpg"
def test_dedupes_urls(self):
html = '
'
imgs = extract_image_urls_from_html(html, base_url="https://example.com/")
assert len(imgs) == 1
def test_malformed_html_does_not_crash(self):
html = "
'
imgs = extract_image_urls_from_html(html, base_url="https://example.com/")
assert len(imgs) == 1
assert imgs[0]["url"] == "https://example.com/lazy.jpg"
def test_dedupes_urls(self):
html = '