feat: 旧検索ページから最新取得（暫定）（#2） (#6)

#2

Co-authored-by: miteruzo <miteruzo@naver.com>
Reviewed-on: #6

.gitignore

@@ -0,0 +1 @@
+__pycache__

__init__.py

@@ -1 +1,8 @@
-from .module import VideoInfo, fetch_comments, fetch_embed_info, fetch_video_info
+"""
+ニコニコ動画から情報取得するためのユーティリティ
+"""
+
+from .module import (VideoInfo,
+                     fetch_embed_info,
+                     fetch_latest_video,
+                     fetch_video_info)

module.py

@@ -1,10 +1,10 @@
+"""
+ニコニコ動画から動画情報を取得するためのヘルパ集
+"""
+
 from __future__ import annotations
 
-import json
-import random
-import string
-import time
-from typing import Any, TypedDict
+from typing import TypedDict
 
 import requests
 from bs4 import BeautifulSoup
@@ -14,6 +14,20 @@ from requests.exceptions import Timeout
 def fetch_video_info (
         video_code: str,
 ) -> VideoInfo | None:
+    """
+    動画コードからタイトル、タグ、説明を取得して返す．
+
+    Parameters
+    ----------
+    video_code: str
+        動画コード
+
+    Return
+    ------
+    VideoInfo | None
+        動画情報
+    """
+
     bs = _create_bs_from_url (f"https://www.nicovideo.jp/watch/{ video_code }")
     if bs is None:
         return None
@@ -24,11 +38,14 @@ def fetch_video_info (
             return None
         title = '-'.join (title_tag.text.split ('-')[:(-1)]).strip ()
 
-        tags_str: str = bs.find ('meta', attrs = { 'name': 'keywords' }).get ('content') # type: ignore
+        tags_str: str = (bs.find ('meta', attrs = { 'name': 'keywords' })
+                         .get ('content'))  # type: ignore
         tags = tags_str.split (',')
 
-        description = bs.find ('meta', attrs = { 'name': 'description' }).get ('content') # type: ignore
-    except (AttributeError, TypeError):
+        description = (bs.find ('meta', attrs = { 'name': 'description' })
+                       .get ('content'))  # type: ignore
+    except (AttributeError, TypeError) as ex:
+        print (ex)
         return None
 
     return { 'contentId':   video_code,
@@ -37,59 +54,26 @@ def fetch_video_info (
              'description': str (description) }
 
 
-def fetch_comments (
-        video_code: str,
-) -> list[Comment]:
-    time.sleep (1.2)
-
-    headers = { 'X-Frontend-Id':      '6',
-                'X-Frontend-Version': '0' }
-
-    action_track_id = (
-            ''.join (random.choice (string.ascii_letters + string.digits)
-                     for _ in range (10))
-            + '_'
-            + str (random.randrange (10 ** 12, 10 ** 13)))
-
-    url = (f"https://www.nicovideo.jp/api/watch/v3_guest/{ video_code }"
-            + f"?actionTrackId={ action_track_id }")
-
-    res = requests.post (url, headers = headers, timeout = 60).json ()
-
-    try:
-        nv_comment = res['data']['comment']['nvComment']
-    except KeyError:
-        return []
-    if nv_comment is None:
-        return []
-
-    headers = { 'X-Frontend-Id':        '6',
-                'X-Frontend-Version':   '0',
-                'Content-Type':         'application/json' }
-
-    params = { 'params':        nv_comment['params'],
-               'additionals':   { },
-               'threadKey':     nv_comment['threadKey'] }
-
-    url = nv_comment['server'] + '/v1/threads'
-
-    res = (requests.post (url, json.dumps (params),
-                          headers = headers,
-                          timeout = 60)
-            .json ())
-
-    try:
-        return res['data']['threads'][1]['comments']
-    except (IndexError, KeyError):
-        return []
-
-
 def fetch_embed_info (
         url:    str,
 ) -> tuple[str, str, str]:
-    title:          str = ''
-    description:    str = ''
-    thumbnail:      str = ''
+    """
+    ニコニコ動画の URL からタイトル、詳細、サムネールを取得して返す．
+
+    Parameters
+    ----------
+    url:    str
+        動画 URL
+
+    Return
+    ------
+    tuple[str, str, str]
+        タイトル、詳細、サムネールからなるタプル
+    """
+
+    title = ''
+    description = ''
+    thumbnail = ''
 
     bs = _create_bs_from_url (url)
     if bs is None:
@@ -103,29 +87,88 @@ def fetch_embed_info (
     if tmp is not None and hasattr (tmp, 'get'):
         try:
             description = str (tmp.get ('content'))
-        except Exception:
-            pass
+        except (AttributeError, TypeError) as ex:
+            print (ex)
 
     tmp = bs.find ('meta', attrs = { 'name': 'thumbnail' })
     if tmp is not None and hasattr (tmp, 'get'):
         try:
             thumbnail = str (tmp.get ('content'))
-        except Exception:
-            pass
+        except (AttributeError, TypeError) as ex:
+            print (ex)
 
     return (title, description, thumbnail)
 
 
+def fetch_latest_video (
+        tags:   list[str],
+) -> VideoInfo | None:
+    """
+    ニコニコから指定したタグが含まれる動画を検索し，最新のものを返す．
+
+    Parameters
+    ----------
+    tags:   list[str]
+        タグ・リスト
+
+    Return
+    ------
+    VideoInfo | None
+        動画情報
+    """
+
+    tag = ' OR '.join (tags)
+    url = f"https://www.nicovideo.jp/tag/{ tag }"
+
+    params = { 'new_search':    'false',
+               'sort':          'f',
+               'order':         'd' }
+
+    video_info = { }
+
+    bs = _create_bs_from_url (url, params)
+    if bs is None:
+        return None
+
+    try:
+        video = (bs.find_all ('ul', class_ = 'videoListInner')[1]
+                 .find ('li', class_ = 'item'))
+
+        video_info['contentId'] = video['data-video-id']
+    except (AttributeError, IndexError, KeyError, TypeError) as ex:
+        print (ex)
+        return None
+
+    return fetch_video_info (video_info['contentId'])
+
+
 def _create_bs_from_url (
         url:    str,
         params: dict | None = None,
 ) -> BeautifulSoup | None:
+    """
+    URL から BeautifulSoup オブゼクトを作成する．
+
+    Parameters
+    ----------
+    url:    str
+        URL
+    params: dict | None
+        パラメータ
+
+    Return
+    ------
+    BeautifulSoup | None
+        BeautifulSoup オブゼクト
+    """
+
     if params is None:
         params = { }
 
     try:
         req = requests.get (url, params = params, timeout = 60)
-    except Timeout:
+    except Timeout as ex:
+        print (ex)
         return None
 
     if req.status_code != 200:
@@ -137,23 +180,11 @@ def _create_bs_from_url (
 
 
 class VideoInfo (TypedDict):
+    """
+    動画情報
+    """
+
     contentId:      str
     title:          str
     tags:           list[str]
     description:    str
-
-
-class Comment (TypedDict):
-    id:             str
-    no:             int
-    vposMs:         int
-    body:           str
-    commands:       list[str]
-    userId:         str
-    isPremium:      bool
-    score:          int
-    postedAt:       str
-    nicoruCount:    int
-    nicoruId:       Any
-    source:         str
-    isMyPost:       bool