Merge branch 'develop'

MANIFEST.in

@@ -0,0 +1,2 @@
+include requirements.txt    
+global-exclude pytchat/testrun*.py

README.md

@@ -0,0 +1,61 @@
+## Install
+```bash
+pip install yvi
+```
+
+
+## Usage
+```python
+import yvi
+
+info = yvi.get_info(video_id = "xxxxxxxx")
+info.get_title()
+info.get_channel_id()
+```
+## Function
+### get_info(video_id, session)
+
+Returns
+-------
++ VideoInfo object.
+
+Parameters
+----------
+- video_id : video id
+
+- session : session object of requests.
+
+
+## Attributes of VideoInfo object
+###    get_duration()
+-     動画の長さ（アーカイブのみ。ライブ動画または待機画面の場合0）
+
+###    get_title()
+- 　　動画タイトル
+
+###    get_title_escaped()
+- 　　動画タイトル(絵文字なし。GUIライブラリ等で絵文字が含まれていてエラーが出る場合はこちらを使用してください)
+
+###    get_channel_id()
+- チャンネルID
+
+###    get_thumbnail()
+- 　　動画サムネイルURL
+
+###    get_owner_name()
+- 　　配信者名
+
+###    get_owner_name_escaped()
+- 　　配信者名(絵文字なし)
+
+###    get_owner_image()
+- 　　配信者プロフィール画像URL
+
+###    get_user_name()
+- 　　視聴者名
+
+###    get_user_name_escaped()
+- 　　視聴者名(絵文字なし)
+
+###    get_user_image()
+- 　　視聴者プロフィール画像URL

requirements.txt

@@ -0,0 +1 @@
+requests

setup.py

@@ -0,0 +1,62 @@
+from setuptools import setup, find_packages, Command
+from os import path, system, remove, rename, removedirs
+import re
+
+package_name = "yvi"
+
+root_dir = path.abspath(path.dirname(__file__))
+
+def _requirements():
+    return [name.rstrip() 
+        for name in open(path.join(
+            root_dir, 'requirements.txt')).readlines()]
+
+with open(path.join(root_dir, package_name, '__init__.py')) as f:
+    init_text = f.read()
+    version = re.search(
+        r'__version__\s*=\s*[\'\"](.+?)[\'\"]', init_text).group(1)
+    license = re.search(
+        r'__license__\s*=\s*[\'\"](.+?)[\'\"]', init_text).group(1)
+    author = re.search(
+        r'__author__\s*=\s*[\'\"](.+?)[\'\"]', init_text).group(1)
+    author_email = re.search(
+        r'__author_email__\s*=\s*[\'\"](.+?)[\'\"]', init_text).group(1)
+    url = re.search(
+        r'__url__\s*=\s*[\'\"](.+?)[\'\"]', init_text).group(1)
+
+assert version
+assert license
+assert author
+assert author_email
+assert url
+
+
+
+
+with open('README.md', encoding='utf-8') as f:
+    long_description = f.read()
+
+
+
+setup(
+    author=author,
+    author_email=author_email,
+    classifiers=[
+        'Natural Language :: Japanese',
+        'Development Status :: 4 - Beta',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 3.7',        
+        'Programming Language :: Python :: 3.8',        
+        'License :: OSI Approved :: MIT License',
+    ],
+    description="Retrieve youtube video info.",
+    install_requires=_requirements(),
+    keywords='youtube',
+    license=license,
+    long_description=long_description,
+    long_description_content_type='text/markdown',
+    name=package_name,
+    packages=find_packages(exclude=['*log.txt','*tests','*testrun']),
+    url=url,
+    version=version,
+)

yvi/__init__.py

@@ -0,0 +1,12 @@
+"""
+Retriever tool for youtube video information.
+"""
+__copyright__    = 'Copyright (C) 2020 taizan-hokuto'
+__version__      = '0.0.1'
+__license__      = 'MIT'
+__author__       = 'taizan-hokuto'
+__author_email__ = '55448286+taizan-hokuto@users.noreply.github.com'
+__url__          = 'https://github.com/taizan-hokuto/yvi'
+
+from yvi.yvi import get_info
+

yvi/config/__init__.py

@@ -0,0 +1,2 @@
+headers = {
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'}

yvi/exceptions.py

@@ -0,0 +1,9 @@
+class InvalidVideoIdException(Exception):
+    '''
+    Thrown when the video_id is not exist (VideoInfo).
+    '''
+    pass
+
+
+class UnknownConnectionError(Exception):
+    pass

yvi/util/__init__.py

@@ -0,0 +1,21 @@
+import datetime
+
+def save(data,filename,extention):
+    with open(filename+"_"+(datetime.datetime.now().strftime('%Y-%m-%d %H-%M-%S')
+                            )+extention,mode ='w',encoding='utf-8') as f:
+        f.writelines(data)
+
+def get_item(dict_body, items: list):
+    for item in items:
+        if dict_body is None:
+            break
+        if isinstance(dict_body, dict):
+            dict_body = dict_body.get(item)
+            continue
+        if isinstance(item, int) and \
+            isinstance(dict_body, list) and \
+            len(dict_body) > item:
+            dict_body = dict_body[item]
+            continue
+        return None
+    return dict_body

yvi/yvi.py

@@ -0,0 +1,194 @@
+from . import config
+import emoji
+import json
+import re
+import requests
+from . import util
+from . exceptions import InvalidVideoIdException
+
+pattern = re.compile(r"yt\.setConfig\({'PLAYER_CONFIG': ({.*})}\);")
+
+item_channel_id = [
+    "videoDetails",
+    "embeddedPlayerOverlayVideoDetailsRenderer",
+    "channelThumbnailEndpoint",
+    "channelThumbnailEndpoint",
+    "urlEndpoint",
+    "urlEndpoint",
+    "url"
+]
+
+item_renderer = [
+    "embedPreview",
+    "thumbnailPreviewRenderer"
+]
+
+item_response = [
+    "args",
+    "embedded_player_response"
+]
+
+item_owner_image = [
+    "videoDetails",
+    "embeddedPlayerOverlayVideoDetailsRenderer",
+    "channelThumbnail",
+    "thumbnails",
+    0,
+    "url"
+]
+
+item_thumbnail = [
+    "defaultThumbnail",
+    "thumbnails",
+    2,
+    "url"
+]
+
+item_owner_name = [
+    "videoDetails",
+    "embeddedPlayerOverlayVideoDetailsRenderer",
+    "expandedRenderer",
+    "embeddedPlayerOverlayVideoDetailsExpandedRenderer",
+    "title",
+    "runs",
+    0,
+    "text"
+]
+
+item_user_name = [
+    "args",
+    "user_display_name",
+]
+
+item_user_image = [
+    "args",
+    "user_display_image",
+]
+
+
+class VideoInfo:
+    '''
+    VideoInfo object retrieves YouTube video information.
+
+    Parameter
+    ---------
+    video_id : str
+
+    Exception
+    ---------
+    InvalidVideoIdException :
+        Occurs when video_id does not exist on YouTube.
+    '''
+
+    def __init__(self, video_id, session:requests.Session = None):
+        if session:
+            self.session = session
+        else:
+            self.session = requests.Session()
+
+        self.video_id = video_id
+        text = self._get_page_text(video_id)
+        self._parse(text)
+
+    def _get_page_text(self, video_id):
+        url = f"https://www.youtube.com/embed/{video_id}"
+        resp = self.session.get(url)
+        resp.raise_for_status()
+        return resp.text
+
+    def _parse(self, text):
+        result = re.search(pattern, text)
+        self._res = json.loads(result.group(1))
+        response = self._get_item(self._res, item_response)
+        if response is None:
+            self._check_video_is_private(self._res.get("args"))
+        
+        self._renderer = self._get_item(json.loads(response), item_renderer)
+        if self._renderer is None:
+            raise InvalidVideoIdException(
+                f"No renderer found in video_id: [{self.video_id}].")
+
+    def _check_video_is_private(self, args):
+        if args and args.get("video_id"):
+            raise InvalidVideoIdException(
+                f"video_id [{self.video_id}] is private or deleted.")
+        raise InvalidVideoIdException(
+            f"video_id [{self.video_id}] is invalid.")
+
+    def _get_item(self, dict_body, items: list):
+        for item in items:
+            if dict_body is None:
+                break
+            if isinstance(dict_body, dict):
+                dict_body = dict_body.get(item)
+                continue
+            if isinstance(item, int) and \
+               isinstance(dict_body, list) and \
+               len(dict_body) > item:
+                dict_body = dict_body[item]
+                continue
+            return None
+        return dict_body
+
+    def get_duration(self):
+        duration_seconds = self._renderer.get("videoDurationSeconds")
+        if duration_seconds:
+            '''Fetched value is string, so cast to integer.'''
+            return int(duration_seconds)
+        '''When key is not found, explicitly returns None.'''
+        return None
+
+    def get_title(self):
+        if self._renderer.get("title"):
+            return [''.join(run["text"])
+                    for run in self._renderer["title"]["runs"]][0]
+        return None
+
+    def get_title_escaped(self):
+        return self._no_emoji(self.get_title())
+
+    def get_channel_id(self):
+        channel_url = self._get_item(self._renderer, item_channel_id)
+        if channel_url:
+            return channel_url[9:]
+        return None
+
+    def get_thumbnail(self):
+        return self._get_item(self._renderer, item_thumbnail)
+
+    def get_owner_image(self):
+        return self._get_item(self._renderer, item_owner_image)
+
+    def get_owner_name(self):
+        return self._get_item(self._renderer, item_owner_name)
+
+    def get_owner_name_escaped(self):
+        return self._no_emoji(self.get_owner_name())
+
+    def get_user_name(self):
+        return self._get_item(self._res, item_user_name)
+
+    def get_user_name_escaped(self):
+        return self._no_emoji(self.get_user_name())
+
+    def get_user_image(self):
+        return self._get_item(self._res, item_user_image)
+
+    def _no_emoji(self, text:str):
+        if text is None:
+            return None
+        return ''.join(c for c in text
+            if c not in emoji.UNICODE_EMOJI)    
+
+def get_info(video_id:str, session:requests.Session = None) -> VideoInfo:
+    """
+    Paaramters
+    ----------
+    video_id : str :
+        video_id
+    
+    session : requests.Session
+        session object
+    """
+
+    return VideoInfo(video_id = video_id, session = session)