initial commit

wowhead_scraper/tests/test_parsers.py

@@ -0,0 +1,110 @@
+from pathlib import Path
+
+import pytest
+
+from parsers import common, quest, object as object_parser
+
+ROOT = Path(__file__).parent.parent
+EXAMPLES = ROOT / "example_pages"
+FIXTURES = Path(__file__).parent / "fixtures"
+
+
+def read(path: Path) -> str:
+    if not path.exists():
+        pytest.skip(f"{path.name} not available")
+    return path.read_text(encoding="utf-8")
+
+
+@pytest.fixture(scope="module")
+def quest_list():
+    return read(EXAMPLES / "https___www.wowhead.com_forever_quests#200.htm")
+
+
+@pytest.fixture(scope="module")
+def object_list():
+    return read(EXAMPLES / "https___www.wowhead.com_forever_objects.htm")
+
+
+def test_quest_list_is_truncated_listview(quest_list):
+    rows, truncated, _ = common.list_page(quest_list, quest.LISTVIEW_ID)
+    assert len(rows) == 1000 and truncated
+
+
+def test_quest_list_row(quest_list):
+    rows, _, _ = common.list_page(quest_list, quest.LISTVIEW_ID)
+    row = quest.list_row(next(r for r in rows if r["id"] == 96393), common.filter_categories(quest_list))
+    assert row == {
+        "id": 96393, "name": "Old Ironforge Incursion", "level": 16, "reqlevel": 9, "side": "Alliance",
+        "category": "The Hall of Thanes", "category_id": 16919, "category2": "Dungeons", "category2_id": 2,
+        "exp": 1450, "money": 800,
+    }
+
+
+def test_category_ids_overlap_between_levels(quest_list):
+    categories = common.filter_categories(quest_list)
+    assert categories[1][0] == "Kalimdor"
+    assert categories[0][1][1] == "Dun Morogh"  # zone 1 under Eastern Kingdoms
+
+
+def test_object_list_uses_json_script(object_list):
+    rows, truncated, _ = common.list_page(object_list, object_parser.LISTVIEW_ID)
+    assert len(rows) == 1000 and truncated
+    row = object_parser.list_row(next(r for r in rows if r["id"] == 3689), common.filter_categories(object_list))
+    assert row == {"id": 3689, "name": "Weapon Crate", "type": "Containers", "type_id": 3, "skill": 0,
+                   "zone_ids": "17;331"}
+
+
+def test_quest_page_baron_marinous():
+    html = read(EXAMPLES / "https___www.wowhead.com_forever_quest=98028_baron-marinous.htm")
+    q = quest.parse_page(html, {"id": "98028", "category": "Darkshore"})
+    assert q["name"] == "Baron Marinous"
+    assert (q["level"], q["reqlevel"], q["side"]) == (21, 17, "Alliance")
+    assert q["objectives"] == "Bring the Clouded Water Globe to Onu at the Grove of the Ancients in Darkshore."
+    assert q["objective_items"] == [{"type": "item", "id": 279275, "name": "Clouded Water Globe",
+                                     "quantity": 1, "standing": None, "provided": True}]
+    assert q["description"].startswith("All that remains of the powerful elemental")
+    assert q["progress"].startswith("I can sense something far older")
+    assert "\n\nStairs descending down in Mathystra?" in q["completion"]
+    assert q["start"] == []
+    assert q["end"] == [{"type": "npc", "id": 3616, "name": "Onu"}]
+    assert q["locations"][0] == {"role": "end", "type": "npc", "id": 3616, "name": "Onu", "zone_id": 148,
+                                 "zone": "Darkshore", "coord": [43.6, 76.4], "coords": [[43.4, 76.2], [43.6, 76.4]]}
+    assert q["rewards"]["xp"] == 1650
+    assert q["rewards"]["money"] == 0
+    assert [i["name"] for i in q["rewards"]["item_choices"]] == ["Mathystra Channeling Orb", "Onu's Patience"]
+    assert q["rewards"]["reputation"] == [{"faction_id": 69, "faction": "Darnassus", "value": 150}]
+    assert "Not sharable" in q["quick_facts"]
+
+
+def test_quest_page_with_giver_and_series():
+    q = quest.parse_page(read(FIXTURES / "quest_166.html"), {"id": "166"})
+    assert q["start"] == [{"type": "npc", "id": 234, "name": "Gryan Stoutmantle"}]
+    giver = next(loc for loc in q["locations"] if loc["role"] == "start")
+    assert (giver["name"], giver["zone"], giver["coord"]) == ("Gryan Stoutmantle", "Westfall", [56.2, 47.6])
+    assert q["series"] == [{"id": 155, "name": "The Defias Brotherhood"},
+                           {"id": 166, "name": "The Defias Brotherhood"}]
+
+
+def test_object_page_weapon_crate():
+    html = read(EXAMPLES / "https___www.wowhead.com_forever_object=3689_weapon-crate.htm")
+    o = object_parser.parse_page(html, {"id": "3689", "type": "Containers", "skill": "0"})
+    assert (o["name"], o["type"], o["type_id"], o["skill"]) == ("Weapon Crate", "Containers", 3, 0)
+    assert [(loc["zone"], loc["count"]) for loc in o["locations"]] == [("The Barrens", 16), ("Ashenvale", 7)]
+    assert len(o["locations"][0]["coords"]) == 16
+    bludgeon = next(i for i in o["contains"] if i["id"] == 1825)
+    assert bludgeon == {"id": 1825, "name": "Bulky Bludgeon", "count": 17, "percent": 0.4, "stack": [1, 1]}
+
+
+def test_object_page_starts_and_ends_quests():
+    o = object_parser.parse_page(read(FIXTURES / "object_415106.html"), {"id": "415106"})
+    assert [q["id"] for q in o["starts"]] == [79007, 79192]
+    assert [q["id"] for q in o["ends"]] == [79008]
+    assert o["contains"] == []
+
+
+def test_quest_page_with_reputation_objectives():
+    q = quest.parse_page(read(FIXTURES / "quest_1036.html"), {"id": "1036"})
+    assert [(o["type"], o["id"], o["name"], o["quantity"], o["standing"]) for o in q["objective_items"]] == [
+        ("faction", 87, "Bloodsail Buccaneers", None, "Friendly"),
+        ("faction", 21, "Booty Bay", None, "Hated"),
+    ]