AtCoderStudyBooster 0.2__py3-none-any.whl → 0.3.1__py3-none-any.whl

atcdr/util/parse.py

@@ -0,0 +1,206 @@
+import re
+from typing import Dict, Iterator, List, Optional
+
+from bs4 import BeautifulSoup as bs
+from bs4 import Tag
+from markdownify import MarkdownConverter
+
+
+class HTML:
+    def __init__(self, html: str) -> None:
+        self.soup = bs(html, 'html.parser')
+        self.title = self._get_title()
+        self.link = self._find_link()
+
+    def _get_title(self) -> str:
+        title_tag = self.soup.title
+        return title_tag.string.strip() if title_tag else ''
+
+    def _find_link(self) -> str:
+        meta_tag = self.soup.find('meta', property='og:url')
+        if isinstance(meta_tag, Tag) and 'content' in meta_tag.attrs:
+            content = meta_tag['content']
+            if isinstance(content, list):
+                return content[0]  # 必要に応じて、最初の要素を返す
+            return content
+        return ''
+
+    @property
+    def html(self) -> str:
+        return str(self.soup)
+
+    def __str__(self) -> str:
+        return self.html
+
+    def __bool__(self) -> bool:
+        return bool(self.html)
+
+
+class CustomMarkdownConverter(MarkdownConverter):
+    def convert_var(self, el, text, convert_as_inline):
+        var_text = el.text.strip()
+        return f'\\({var_text}\\)'
+
+    def convert_pre(self, el, text, convert_as_inline):
+        pre_text = el.text.strip()
+        return f'```\n{pre_text}\n```'
+
+
+class ProblemForm(Tag):
+    def find_submit_link(self) -> str:
+        action = self['action']
+        submit_url = f'https://atcoder.jp{action}'
+        return submit_url
+
+    def find_task_screen_name(self) -> str:
+        task_input = self.find('input', {'name': 'data.TaskScreenName'})
+        task_screen_name = task_input['value']
+        return task_screen_name
+
+    def get_languages_options(self) -> Dict[str, int]:
+        options: Iterator[Tag] = self.find_all('option')
+
+        options = filter(
+            lambda option: 'value' in option.attrs and option['value'].isdigit(),
+            options,
+        )
+        return {option.text.strip(): int(option['value']) for option in options}
+
+
+class ProblemHTML(HTML):
+    def repair_me(self) -> None:
+        html = self.html.replace('//img.atcoder.jp', 'https://img.atcoder.jp')
+        html = html.replace(
+            '<meta http-equiv="Content-Language" content="en">',
+            '<meta http-equiv="Content-Language" content="ja">',
+        )
+        html = html.replace('LANG = "en"', 'LANG="ja"')
+        self.soup = bs(html, 'html.parser')
+
+    def abstract_problem_part(self, lang: str) -> Optional[Tag]:
+        task_statement = self.soup.find('div', {'id': 'task-statement'})
+        if not isinstance(task_statement, Tag):
+            return None
+
+        if lang == 'ja':
+            lang_class = 'lang-ja'
+        elif lang == 'en':
+            lang_class = 'lang-en'
+        else:
+            raise ValueError(f'言語は {lang} に対応していません')
+        span = task_statement.find('span', {'class': lang_class})
+        return span
+
+    def make_problem_markdown(self, lang: str) -> str:
+        title = self.title
+        problem_part = self.abstract_problem_part(lang)
+        if problem_part is None:
+            return ''
+
+        problem_md = CustomMarkdownConverter().convert(str(problem_part))
+        problem_md = f'# {title}\n{problem_md}'
+        problem_md = re.sub(r'\n\s*\n\s*\n+', '\n\n', problem_md).strip()
+        return problem_md
+
+    def load_labeled_testcase(self) -> List:
+        from atcdr.test import LabeledTestCase, TestCase
+
+        problem_part = self.abstract_problem_part('en')
+        if problem_part is None:
+            return []
+
+        sample_inputs = problem_part.find_all(
+            'h3', text=re.compile(r'Sample Input \d+')
+        )
+        ltest_cases = []
+        for i, sample_input_section in enumerate(sample_inputs, start=1):
+            # 対応する Sample Output を取得
+            sample_output_section = problem_part.find('h3', text=f'Sample Output {i}')
+            if not sample_input_section or not sample_output_section:
+                break
+
+            sample_input_pre = sample_input_section.find_next('pre')
+            sample_output_pre = sample_output_section.find_next('pre')
+
+            # 入力と出力をテキスト形式で取得
+            sample_input = (
+                sample_input_pre.get_text(strip=True)
+                if sample_input_pre is not None
+                else ''
+            )
+            sample_output = (
+                sample_output_pre.get_text(strip=True)
+                if sample_output_pre is not None
+                else ''
+            )
+
+            ltest_cases.append(
+                LabeledTestCase(
+                    f'Sample Case {i}', TestCase(sample_input, sample_output)
+                )
+            )
+
+        return ltest_cases
+
+    @property
+    def form(self) -> ProblemForm:
+        form = self.soup.find('form', class_='form-code-submit')
+        if not isinstance(form, Tag):
+            raise ValueError('問題ページにフォームが存在しません')
+        form.__class__ = ProblemForm
+        return form
+
+
+def get_username_from_html(html: str) -> str:
+    soup = bs(html, 'html.parser')
+    script_tags = soup.find_all('script')
+
+    user_screen_name = ''
+    for script in script_tags:
+        # <script>タグに内容がある場合のみ処理を行う
+        if script.string:
+            # 正規表現でuserScreenNameの値を抽出
+            match = re.search(r'userScreenName\s*=\s*"([^"]+)"', script.string)
+            if match:
+                user_screen_name = match.group(1)
+                break  # 見つかったらループを抜ける
+
+    return user_screen_name
+
+
+def get_csrf_token(html_content: str) -> str:
+    soup = bs(html_content, 'html.parser')
+    csrf_token = soup.find('input', {'name': 'csrf_token'})['value']
+    return csrf_token if csrf_token else ''
+
+
+def get_problem_urls_from_tasks(html_content: str) -> list[tuple[str, str]]:
+    soup = bs(html_content, 'html.parser')
+    table = soup.find('table')
+    if not table:
+        raise ValueError('問題のテーブルが見つかりませんでした.')
+
+    # tbodyタグを見つける
+    tbody = table.find('tbody')
+    if not tbody:
+        raise ValueError('tbodyが見つかりませんでした.')
+
+    # tbody内の1列目のaタグのリンクと中身を取得
+    links = []
+    for row in tbody.find_all('tr'):
+        first_column = row.find('td')
+        a_tag = first_column.find('a')
+        if a_tag and 'href' in a_tag.attrs:
+            link = 'https://atcoder.jp' + a_tag['href']
+            label = a_tag.text.strip()
+            links.append((label, link))
+
+    return links
+
+
+def get_submission_id(html_content: str) -> Optional[int]:
+    soup = bs(html_content, 'html.parser')
+    first_tr = soup.select_one('tbody > tr')
+    data_id_td = first_tr.find(lambda tag: tag.has_attr('data-id'))
+    data_id = int(data_id_td['data-id']) if data_id_td else None
+    return data_id

atcdr/util/problem.py

@@ -1,91 +1,94 @@
-import re
-from enum import Enum
-from typing import Match, Optional
-
-from bs4 import BeautifulSoup as bs
-from bs4 import Tag
-from markdownify import MarkdownConverter  # type: ignore
-
-
-def repair_html(html: str) -> str:
-	html = html.replace('//img.atcoder.jp', 'https://img.atcoder.jp')
-	html = html.replace(
-		'<meta http-equiv="Content-Language" content="en">',
-		'<meta http-equiv="Content-Language" content="ja">',
-	)
-	html = html.replace('LANG = "en"', 'LANG="ja"')
-	html = remove_unnecessary_emptylines(html)
-	return html
-
-
-def get_title_from_html(html: str) -> str:
-	title: Optional[Match[str]] = re.search(r'<title>([^<]*)</title>', html)
-	return title.group(1).strip() if title else ''
-
-
-def title_to_filename(title: str) -> str:
-	title = re.sub(r'[\\/*?:"<>| !@#$%^&()+=\[\]{};,\']', '', title)
-	title = re.sub(r'^[A-Z]-', '', title)
-	return title
-
-
-def find_link_from_html(html: str) -> str:
-	soup = bs(html, 'html.parser')
-	meta_tag = soup.find('meta', property='og:url')
-	if isinstance(meta_tag, Tag) and 'content' in meta_tag.attrs:
-		content = meta_tag['content']
-		if isinstance(content, list):
-			return content[0]  # 必要に応じて、最初の要素を返す
-		return content
-	return ''
-
-
-class Lang(Enum):
-	JA = 'ja'
-	EN = 'en'
-
-
-class CustomMarkdownConverter(MarkdownConverter):
-	def convert_var(self, el, text, convert_as_inline):
-		var_text = el.text.strip()
-		return f'\\({var_text}\\)'
-
-	def convert_pre(self, el, text, convert_as_inline):
-		pre_text = el.text.strip()
-		return f'```\n{pre_text}\n```'
-
-
-def custom_markdownify(html, **options):
-	return CustomMarkdownConverter(**options).convert(html)
-
-
-def remove_unnecessary_emptylines(text):
-	text = re.sub(r'\n\s*\n\s*\n+', '\n\n', text)
-	text = text.strip()
-	return text
-
-
-def abstract_problem_part(html_content: str, lang: str) -> str:
-	soup = bs(html_content, 'html.parser')
-	task_statement = soup.find('div', {'id': 'task-statement'})
-
-	if not isinstance(task_statement, Tag):
-		return ''
-
-	if lang == 'ja':
-		lang_class = 'lang-ja'
-	elif lang == 'en':
-		lang_class = 'lang-en'
-	else:
-		pass
-	span = task_statement.find('span', {'class': lang_class})
-	return str(span)
-
-
-def make_problem_markdown(html_content: str, lang: str) -> str:
-	title = get_title_from_html(html_content)
-	problem_part = abstract_problem_part(html_content, lang)
-	problem_md = custom_markdownify(problem_part)
-	problem_md = f'# {title}\n{problem_md}'
-	problem_md = remove_unnecessary_emptylines(problem_md)
-	return problem_md
+from typing import List, Optional
+
+import requests
+
+from atcdr.util.parse import get_problem_urls_from_tasks
+
+
+class Contest:
+    def __init__(self, name: str, number: Optional[int] = None):
+        if not name:
+            raise ValueError('nameは必須です')
+        self._name = name
+        self._number = number
+        if number and number > 0:
+            self._contest = f'{name}{number:03}'
+        else:
+            self._contest = name
+
+    @property
+    def contest(self) -> str:
+        return self._contest
+
+    @property
+    def number(self) -> Optional[int]:
+        return self._number
+
+    @property
+    def url(self) -> str:
+        return f'https://atcoder.jp/contests/{self.contest}/tasks'
+
+    def __str__(self) -> str:
+        return f'{self.contest}'
+
+    def __repr__(self) -> str:
+        return f'Contest(name={self._name}, number={self._number})'
+
+    def problems(self, session: Optional[requests.Session] = None) -> List['Problem']:
+        session = session or requests.Session()
+        response = session.get(self.url)
+
+        if response.status_code != 200:
+            return []
+
+        return [
+            Problem(self, label=label, url=url)
+            for label, url in get_problem_urls_from_tasks(response.text)
+        ]
+
+
+class Diff(str):
+    def __new__(cls, diff: str) -> 'Diff':
+        if isinstance(diff, str) and len(diff) == 1 and diff.isalpha():
+            return super().__new__(cls, diff.upper())
+        raise ValueError('diffは英大文字または小文字の1文字である必要があります')
+
+    def __repr__(self) -> str:
+        return f"Diff('{self}')"
+
+
+class Problem:
+    def __init__(
+        self,
+        contest: Contest,
+        difficulty: Optional[Diff] = None,
+        label: Optional[str] = None,
+        url: Optional[str] = None,
+    ):
+        self._contest = contest
+        if difficulty:
+            self._label = difficulty.upper()
+            self._url = contest.url + f'/{contest}_{difficulty.lower()}'
+        elif label and url:
+            self._label = label
+            self._url = url
+        else:
+            raise ValueError('labelとurlは両方必須かdifficultyが必要です')
+
+    @property
+    def contest(self) -> Contest:
+        return self._contest
+
+    @property
+    def label(self) -> str:
+        return self._label
+
+    @property
+    def url(self) -> str:
+        return self._url
+
+    def __repr__(self) -> str:
+        return f'Problem(contest={self.contest}, label={self.label}, url={self.url})'
+
+    def __str__(self) -> str:
+        return f'{self.contest} {self.label}'

atcdr/util/session.py

@@ -0,0 +1,140 @@
+import json
+import os
+from urllib.parse import unquote
+
+import requests
+from rich import print
+from rich.align import Align
+from rich.panel import Panel
+from rich.syntax import Syntax
+from rich.table import Table
+
+from atcdr.util.parse import get_username_from_html
+
+COOKIE_PATH = os.path.join(os.path.expanduser('~'), '.cache', 'atcdr', 'session.json')
+
+
+# デバック用のレスポンス解析用関数
+def print_rich_response(
+    response: requests.Response, body_range: tuple = (0, 24)
+) -> None:
+    # レスポンス情報をテーブル形式で表示
+    info_table = Table(title='レスポンス情報')
+    info_table.add_column('項目', justify='left', style='cyan', no_wrap=True)
+    info_table.add_column('内容', justify='left', style='magenta')
+    info_table.add_row('URL', response.url)
+    info_table.add_row('ステータスコード', str(response.status_code))
+    info_table.add_row('理由', response.reason)
+    info_table = Align.center(info_table)
+
+    # ヘッダー情報をテーブル形式で表示
+    header_table = Table(title='レスポンスヘッダー')
+    header_table.add_column('キー', style='cyan', no_wrap=True)
+    header_table.add_column('値', style='magenta', overflow='fold')
+    for key, value in response.headers.items():
+        value = unquote(value)
+        header_table.add_row(key, value)
+    header_table = Align.center(header_table)
+
+    # リダイレクトの歴史
+    redirect_table = None
+    if response.history:
+        redirect_table = Table(title='リダイレクト履歴')
+        redirect_table.add_column('ステップ', style='cyan')
+        redirect_table.add_column('ステータスコード', style='magenta')
+        redirect_table.add_column('URL', style='green')
+        for i, redirect_response in enumerate(response.history):
+            redirect_table.add_row(
+                f'Redirect {i}',
+                str(redirect_response.status_code),
+                redirect_response.url,
+            )
+        redirect_table = Align.center(redirect_table)
+
+    # レスポンスボディの表示
+    content_type = response.headers.get('Content-Type', '').lower()
+    if 'application/json' in content_type:
+        # JSONの整形表示
+        try:
+            body = Syntax(
+                json.dumps(response.json(), indent=4),
+                'json',
+                theme='monokai',
+                line_numbers=True,
+                line_range=body_range,
+                word_wrap=True,
+            )
+        except Exception:
+            pass
+    else:
+        # HTMLやその他のコンテンツの整形表示
+        body = (
+            Syntax(
+                response.text,
+                'html' if 'html' in content_type else 'text',
+                theme='monokai',
+                line_numbers=True,
+                line_range=body_range,
+                word_wrap=True,
+            )
+            if response.text
+            else None
+        )
+    body_panel = Panel(body, title='レスポンスボディ') if body else None
+
+    print(info_table)
+    print(header_table)
+    if redirect_table:
+        print(redirect_table)
+    if body:
+        print(body_panel)
+
+
+def load_session() -> requests.Session:
+    ATCODER_URL = 'https://atcoder.jp'
+    if not os.path.exists(COOKIE_PATH):
+        return requests.Session()
+    else:
+        with open(COOKIE_PATH) as file:
+            session = requests.Session()
+            session.cookies.update(json.load(file))
+        if validate_session(session):
+            response = session.get(ATCODER_URL)
+            username = get_username_from_html(response.text)
+            if username:
+                print(f'こんにちは！[cyan]{username}[/] さん')
+            return session
+        else:
+            return requests.Session()
+
+
+def save_session(session: requests.Session) -> None:
+    if validate_session(session):
+        os.makedirs(os.path.dirname(COOKIE_PATH), exist_ok=True)
+        with open(COOKIE_PATH, 'w') as file:
+            json.dump(session.cookies.get_dict(), file)
+    else:
+        pass
+
+
+def validate_session(session: requests.Session) -> bool:
+    ATCODER_SETTINGS_URL = 'https://atcoder.jp/settings'
+    try:
+        response = session.get(
+            ATCODER_SETTINGS_URL, allow_redirects=False
+        )  # リダイレクトを追跡しない
+        if response.status_code == 200:
+            return True
+        elif response.status_code in (301, 302) and 'Location' in response.headers:
+            redirect_url = response.headers['Location']
+            if 'login' in redirect_url:
+                return False
+        return False
+    except requests.RequestException as e:
+        print(f'[red][-][/] セッションチェック中にエラーが発生しました: {e}')
+        return False
+
+
+def delete_session() -> None:
+    if os.path.exists(COOKIE_PATH):
+        os.remove(COOKIE_PATH)