Files
miem_workers/tests/test_parser.py

235 lines
9.7 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
from bs4 import BeautifulSoup
from app.parser.profile import enrich_sections_from_hse_widgets, extract_person_tabs, extract_sections
from app.parser.profile_url import normalize_profile_url, parse_profile_identity
class FakeResponse:
def __init__(self, payload):
self.payload = payload
def raise_for_status(self):
return None
def json(self):
return self.payload
class FakeSession:
def __init__(self):
self.posts = []
self.gets = []
def post(self, url, **kwargs):
self.posts.append((url, kwargs))
return FakeResponse(
{
"status": "ok",
"result": {
"more": False,
"total": 1,
"items": [
{
"id": "888959076",
"type": "ARTICLE",
"title": "Дублирование пакетов",
"year": 2023,
"language": {"name": "ru"},
"status": 1,
"authorsByType": {
"author": [
{
"id": "568398853",
"href": "/org/persons/568398853",
"title": {"ru": "Левицкий И. А.", "en": ""},
"reverseTitle": {"ru": "И. А. Левицкий", "en": ""},
}
]
},
"description": {"short": {"ru": "Информационные процессы. 2023."}},
"annotation": {"ru": "<p>Русская аннотация</p>"},
"documents": {"DOI": {"href": "https://doi.org/10.1/test"}},
}
],
},
}
)
def get(self, url, **kwargs):
self.gets.append((url, kwargs))
return FakeResponse(
{
"lang": "ru",
"success": True,
"data": [
{
"id": 1045750164,
"year": 2025,
"level": "Бакалавриат",
"title": "Аппаратно-программный комплекс защиты сети",
"rating": 8,
"student": "Лесняк Владислав Евгеньевич",
"learnProgram": {"title": "Информатика и вычислительная техника", "url": "https://hse.ru/ba/isct/"},
"orgUnit": {"title": "МИЭМ", "url": "https://www.hse.ru/org/url/59315150"},
"supervisors": [{"url": "https://www.hse.ru/org/persons/803294906", "name": "Борисов Сергей Петрович"}],
}
],
}
)
class GroupedPublicationsSession(FakeSession):
def post(self, url, **kwargs):
self.posts.append((url, kwargs))
return FakeResponse(
{
"status": "ok",
"result": {
"more": False,
"total": 1,
"groupType": 2,
"items": {
"year": {
"header": {"ru": "по году", "en": "by year"},
"criteria": {"year": []},
"items": {
"2011": [
{
"id": "146366790",
"type": "ARTICLE",
"title": "Развитие теории самосогласованного поля",
"year": 2011,
"description": {"short": {"ru": "Журнал физической химии 2011."}},
}
],
"2012": [
{
"id": "146367323",
"type": "ARTICLE",
"title": "Self-consistent field theory investigation",
"year": 2012,
"description": {"short": {"en": "Russian Journal of Physical Chemistry A 2012."}},
}
],
},
}
},
},
}
)
def test_normalize_profile_url_supports_staff_and_org_persons():
assert normalize_profile_url("/staff/avsergeev#sci") == "https://www.hse.ru/staff/avsergeev"
assert normalize_profile_url("https://www.hse.ru/org/persons/123/") == "https://www.hse.ru/org/persons/123"
assert parse_profile_identity("https://www.hse.ru/staff/avsergeev") == ("staff", "avsergeev")
def test_extract_person_tabs_prefers_person_menu_addition():
soup = BeautifulSoup(
"""
<div class="person-menu is-desktop small person-menu-addition">
<a href="#main">Домашняя страница</a>
<a href="#sci" data-index="1">Публикации</a>
</div>
<a href="/org/persons/999">Other person</a>
""",
"html.parser",
)
tabs = extract_person_tabs(soup, "https://www.hse.ru/staff/avsergeev")
assert [tab["title"] for tab in tabs] == ["Домашняя страница", "Публикации"]
assert tabs[1]["href"] == "https://www.hse.ru/staff/avsergeev#sci"
def test_enrich_sections_from_hse_widgets_loads_publications_and_vkr():
soup = BeautifulSoup(
"""
<script src="/n/stat/publications/dist-w/publs.js" data-author="568398853" data-widget-name="AuthorSearch"></script>
<script src="/n/stat/vkr/app.js" data-api-url="/n/vkr/api/" data-person-id="803294906"></script>
""",
"html.parser",
)
session = FakeSession()
sections = enrich_sections_from_hse_widgets(
session,
soup,
"https://www.hse.ru/org/persons/803294906",
{"User-Agent": "test"},
10,
[],
)
publications = next(section for section in sections if section["type"] == "publications")
theses = next(section for section in sections if section["type"] == "graduation_theses")
assert publications["publications_count"] == 1
assert publications["publications"][0]["url"] == "https://publications.hse.ru/view/888959076"
assert publications["publications"][0]["doi_url"] == "https://doi.org/10.1/test"
assert publications["publications"][0]["annotation"] == {"ru": "Русская аннотация"}
assert publications["publications"][0]["authors"][0]["is_current_employee"] is True
assert theses["theses_count"] == 1
assert theses["theses"][0]["student"] == "Лесняк Владислав Евгеньевич"
assert theses["theses"][0]["project_url"] == "https://www.hse.ru/edu/vkr/1045750164"
assert session.posts[0][0] == "https://publications.hse.ru/api/searchPubs"
assert session.gets[0][1]["params"] == {"supervisorId": "803294906"}
def test_enrich_sections_from_hse_widgets_loads_grouped_publications():
soup = BeautifulSoup(
"""
<script src="/n/stat/publications/dist-w/publs.js" data-author="133709486" data-widget-name="AuthorSearch"></script>
""",
"html.parser",
)
session = GroupedPublicationsSession()
sections = enrich_sections_from_hse_widgets(
session,
soup,
"https://www.hse.ru/org/persons/133709486",
{"User-Agent": "test"},
10,
[],
)
publications = next(section for section in sections if section["type"] == "publications")
assert publications["publications_count"] == 2
assert [item["id"] for item in publications["publications"]] == ["146366790", "146367323"]
assert publications["publications"][0]["url"] == "https://publications.hse.ru/view/146366790"
assert publications["publications"][1]["url"] == "https://publications.hse.ru/view/146367323"
def test_news_heading_with_publications_word_does_not_absorb_widget_publications():
soup = BeautifulSoup(
"""
<h2>Статья профессора МИЭМ вошла в число самых популярных публикаций на портале SpringerLink</h2>
<div class="post__text">
<p>Первоначально статья профессора вышла в российском журнале.</p>
</div>
<script src="/n/stat/publications/dist-w/publs.js" data-author="133709486" data-widget-name="AuthorSearch"></script>
""",
"html.parser",
)
session = FakeSession()
sections = extract_sections(soup, "https://www.hse.ru/org/persons/133709486")
sections = enrich_sections_from_hse_widgets(
session,
soup,
"https://www.hse.ru/org/persons/133709486",
{"User-Agent": "test"},
10,
sections,
)
assert sections[0]["type"] == "paragraphs"
assert sections[0]["title"].startswith("Статья профессора")
publications = [section for section in sections if section["type"] == "publications"]
assert len(publications) == 1
assert publications[0]["title"] == "Публикации и исследования"
assert publications[0]["publications_count"] == 1