49 lines
1.6 KiB
Python
49 lines
1.6 KiB
Python
from scrape_movies.constants import EMPIRE_FIXTURE_PATH
|
|
from scrape_movies.infrastructure import empire_movies
|
|
from scrape_movies.infrastructure.soup_basics import load_html
|
|
|
|
SNAPSHOT_LAYOUT = """
|
|
<h3 class="title">4) The Shawshank Redemption</h3>
|
|
<h3 class="title">3) The Dark Knight</h3>
|
|
<h3 class="other">not a title</h3>
|
|
<h3 class="title">2) The Empire Strikes Back</h3>
|
|
"""
|
|
|
|
|
|
def test_parse_titles_when_snapshot_layout_reads_h3_title_in_page_order() -> None:
|
|
assert empire_movies.parse_titles(SNAPSHOT_LAYOUT) == [
|
|
"4) The Shawshank Redemption",
|
|
"3) The Dark Knight",
|
|
"2) The Empire Strikes Back",
|
|
]
|
|
|
|
|
|
def test_parse_titles_when_live_layout_reads_ranked_h2_headings() -> None:
|
|
titles = empire_movies.parse_titles(load_html(EMPIRE_FIXTURE_PATH))
|
|
assert len(titles) == 100
|
|
assert titles[0].startswith("100) ")
|
|
assert titles[-1].startswith("1) ")
|
|
|
|
|
|
def test_parse_titles_when_h2_has_no_rank_ignores_it() -> None:
|
|
assert empire_movies.parse_titles("<h2>Jump to</h2><h2>2) Two</h2>") == ["2) Two"]
|
|
|
|
|
|
def test_parse_titles_when_page_has_no_titles_returns_empty() -> None:
|
|
assert empire_movies.parse_titles("<p>nothing</p>") == []
|
|
|
|
|
|
def test_first_title_markup_when_snapshot_layout_shows_h3() -> None:
|
|
assert empire_movies.first_title_markup(SNAPSHOT_LAYOUT).startswith(
|
|
'<h3 class="title">'
|
|
)
|
|
|
|
|
|
def test_first_title_markup_when_live_layout_shows_h2() -> None:
|
|
markup = empire_movies.first_title_markup(load_html(EMPIRE_FIXTURE_PATH))
|
|
assert markup.startswith("<h2>")
|
|
|
|
|
|
def test_first_title_markup_when_nothing_found_returns_empty() -> None:
|
|
assert empire_movies.first_title_markup("<p>x</p>") == ""
|