Compare commits

...

47 Commits

Author SHA1 Message Date
taizan-hokuto
b576c3f928 Merge branch 'develop' 2019-12-24 00:57:06 +09:00
taizan-hokuto
c0728e1366 Increment version 2019-12-24 00:55:00 +09:00
taizan-hokuto
fff09d4c27 Fix README 2019-12-24 00:52:53 +09:00
taizan-hokuto
810b6c8c6b Fix README 2019-12-24 00:29:10 +09:00
taizan-hokuto
dfada86caf Merge branch 'develop' 2019-12-22 02:56:54 +09:00
taizan-hokuto
91aa944df5 Increment version 2019-12-22 02:54:20 +09:00
taizan-hokuto
6ac5191e85 Change debug mode 2019-12-22 01:58:42 +09:00
taizan-hokuto
fff3e0371f Export SpeedCalculator 2019-12-22 01:39:35 +09:00
taizan-hokuto
a70efe8a67 Fix comments 2019-12-21 23:42:51 +09:00
taizan-hokuto
dc47f4debe Fix README 2019-12-21 22:40:08 +09:00
taizan-hokuto
ab5a2a8df2 Fix syntax error 2019-12-21 20:12:30 +09:00
taizan-hokuto
5a79f26fa7 Fix calculation algorithm 2019-12-21 20:06:55 +09:00
taizan-hokuto
18666199b7 Add test SpeedCalculator 2019-12-21 02:13:15 +09:00
taizan-hokuto
b357bccb98 Add test json 2019-12-20 23:57:10 +09:00
taizan-hokuto
3c1f079d5f Extends ChatProcessor explicitly 2019-12-20 21:33:32 +09:00
taizan-hokuto
289841a000 Export api speed_calculator 2019-12-20 01:13:50 +09:00
taizan-hokuto
ee0ff7fe74 Merge branch 'develop' 2019-12-19 23:14:37 +09:00
taizan-hokuto
c0870ce537 Fix README 2019-12-19 23:14:05 +09:00
taizan-hokuto
de6ef2490e Merge branch 'develop' 2019-12-19 02:03:09 +09:00
taizan-hokuto
b8bdbdc36f Increment version 2019-12-19 02:02:32 +09:00
taizan-hokuto
9f5d3f323e Fix README 2019-12-19 02:00:41 +09:00
taizan-hokuto
cf9aae3322 Merge branch 'develop' 2019-12-19 01:57:08 +09:00
taizan-hokuto
6ac2315936 Increment version 2019-12-19 01:53:55 +09:00
taizan-hokuto
50c8e34080 Fix README 2019-12-19 01:51:31 +09:00
taizan-hokuto
2d3da91d51 Fix calculation algorithm 2019-12-19 01:21:49 +09:00
taizan-hokuto
3ac71985ff Implement SpeedCalculator 2019-12-17 21:29:20 +09:00
taizan-hokuto
13bdf0376b Merge branch 'develop' 2019-12-01 22:58:53 +09:00
taizan-hokuto
b2ffdaec0c Increment version 2019-12-01 22:54:43 +09:00
taizan-hokuto
c85786679f Merge branch 'feature/1' into develop 2019-12-01 22:50:06 +09:00
taizan-hokuto
c7a7886672 Fix superSticker rendering 2019-12-01 22:47:01 +09:00
taizan-hokuto
12996fb44d Merge branch 'feature/1' 2019-11-22 00:17:15 +09:00
taizan-hokuto
c884ef7288 Merge branch 'feature/1' into develop 2019-11-22 00:16:20 +09:00
taizan-hokuto
2cd9e98fc2 Increment version 2019-11-22 00:15:57 +09:00
taizan-hokuto
2ac4c99ab4 Increment version 2019-11-22 00:04:18 +09:00
taizan-hokuto
51bf8ad738 Update README 2019-11-21 23:37:35 +09:00
taizan-hokuto
2e70e74bcd Update README 2019-11-21 23:04:12 +09:00
taizan-hokuto
a39d6cb420 Use list comprehension 2019-11-21 22:46:15 +09:00
taizan-hokuto
5dd0cb45b7 Implement messageEx 2019-11-21 22:35:27 +09:00
taizan-hokuto
24873651a6 Fix comments 2019-11-21 20:47:42 +09:00
taizan-hokuto
0e060bf998 Use logger when errors occur 2019-11-20 23:59:16 +09:00
taizan-hokuto
817fed9d1d Make functions private. 2019-11-19 20:53:37 +09:00
taizan-hokuto
823f7fefa4 Fix comments 2019-11-19 20:36:54 +09:00
taizan-hokuto
aa894fc52b Fix comments 2019-11-15 00:58:36 +09:00
taizan-hokuto
6d775e5cd0 Merge branch 'hotfix' 2019-11-14 22:39:22 +09:00
taizan-hokuto
53b70ed86b Increment version 2019-11-14 22:38:25 +09:00
taizan-hokuto
68c707b7d6 Update README 2019-11-14 22:37:16 +09:00
taizan-hokuto
30aaa54a2f Change debug mode 2019-11-14 22:34:29 +09:00
22 changed files with 904 additions and 114 deletions

105
README.md
View File

@@ -8,12 +8,12 @@ pytchat is a python library for fetching youtube live chat
without using youtube api, Selenium or BeautifulSoup.
Other features:
+ Customizable chat data processors including yt api compatible one.
+ Customizable chat data processors including youtube api compatible one.
+ Available on asyncio context.
+ Quick fetching of initial chat data by generating continuation params
instead of web scraping.
より詳細な説明は [wiki](https://github.com/taizan-hokuto/pytchat/wiki) をご参照ください。
For more detailed information, see [wiki](https://github.com/taizan-hokuto/pytchat/wiki).
## Install
```python
@@ -29,10 +29,10 @@ from pytchat import LiveChat
chat = LiveChat("G1w62uEMZ74")
while chat.is_alive():
data = chat.get()
for c in data.items:
print(f"{c.datetime} [{c.author.name}]-{c.message} {c.amountString}")
data.tick()
data = chat.get()
for c in data.items:
print(f"{c.datetime} [{c.author.name}]-{c.message} {c.amountString}")
data.tick()
```
### callback mode
@@ -40,15 +40,17 @@ while chat.is_alive():
from pytchat import LiveChat
import time
chat = LiveChat("G1w62uEMZ74", callback = func)
while chat.is_alive():
#other background operation here.
def main()
chat = LiveChat("G1w62uEMZ74", callback = func)
while chat.is_alive():
time.sleep(3)
#other background operation.
#callback function is automatically called periodically.
def func(data):
for c in data.items:
print(f"{c.datetime} [{c.author.name}]-{c.message} {c.amountString}")
data.tick()
for c in data.items:
print(f"{c.datetime} [{c.author.name}]-{c.message} {c.amountString}")
data.tick()
```
### asyncio context:
@@ -57,15 +59,16 @@ from pytchat import LiveChatAsync
import asyncio
async def main():
chat = LiveChatAsync("G1w62uEMZ74", callback = func)
while chat.is_alive():
#other background operation here.
await asyncio.sleep(3)
chat = LiveChatAsync("G1w62uEMZ74", callback = func)
while chat.is_alive():
await asyncio.sleep(3)
#other background operation.
#callback function is automatically called periodically.
async def func(data):
for c in data.items:
print(f"{c.datetime} [{c.author.name}]-{c.message} {c.amountString}")
await data.tick_async()
for c in data.items:
print(f"{c.datetime} [{c.author.name}]-{c.message} {c.amountString}")
await data.tick_async()
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
@@ -77,16 +80,16 @@ loop.run_until_complete(main())
from pytchat import LiveChat, CompatibleProcessor
chat = LiveChat("G1w62uEMZ74",
processor = CompatibleProcessor() )
processor = CompatibleProcessor() )
while chat.is_alive():
data = chat.get()
polling = data["pollingIntervalMillis"]/1000
for c in data["items"]:
if c.get("snippet"):
print(f"[{c['authorDetails']['displayName']}]"
f"-{c['snippet']['displayMessage']}")
time.sleep(polling/len(data["items"]))
data = chat.get()
polling = data["pollingIntervalMillis"]/1000
for c in data["items"]:
if c.get("snippet"):
print(f"[{c['authorDetails']['displayName']}]"
f"-{c['snippet']['displayMessage']}")
time.sleep(polling/len(data["items"]))
```
### replay:
@@ -95,27 +98,28 @@ from pytchat import ReplayChatAsync
import asyncio
async def main():
chat = ReplayChatAsync("G1w62uEMZ74", seektime = 1000, callback = func)
while chat.is_alive():
#other background operation here.
await asyncio.sleep(3)
chat = ReplayChatAsync("G1w62uEMZ74", seektime = 1000, callback = func)
while chat.is_alive():
await asyncio.sleep(3)
#other background operation here.
#callback function is automatically called periodically.
async def func(data):
for count in range(0,len(data.items)):
c= data.items[count]
if count!=len(data.items):
tick=data.items[count+1].timestamp -data.items[count].timestamp
else:
tick=0
print(f"<{c.timestampText}> [{c.author.name}]-{c.message} {c.amountString}")
await asyncio.sleep(tick/1000)
for count in range(0,len(data.items)):
c= data.items[count]
if count!=len(data.items):
tick=data.items[count+1].timestamp -data.items[count].timestamp
else:
tick=0
print(f"<{c.elapsedTime}> [{c.author.name}]-{c.message} {c.amountString}")
await asyncio.sleep(tick/1000)
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
```
## Chatdata Structure of Default Processor
Structure of each item which got from items() function.
## Structure of Default Processor
Each item can be got with items() function.
<table>
<tr>
<th>name</th>
@@ -137,6 +141,11 @@ Structure of each item which got from items() function.
<td>str</td>
<td>emojis are represented by ":(shortcut text):"</td>
</tr>
<tr>
<td>messageEx</td>
<td>str</td>
<td>list of message texts and emoji URLs.</td>
</tr>
<tr>
<td>timestamp</td>
<td>int</td>
@@ -145,26 +154,26 @@ Structure of each item which got from items() function.
<tr>
<td>datetime</td>
<td>str</td>
<td>ex. "2019-10-10 12:34:56"</td>
<td>e.g. "2019-10-10 12:34:56"</td>
</tr>
<td>timestampText</td>
<td>elapsedTime</td>
<td>str</td>
<td>elapsed time. (ex. "1:02:27")</td>
<td>elapsed time. (e.g. "1:02:27") *Replay Only.</td>
</tr>
<tr>
<td>amountValue</td>
<td>float</td>
<td>ex. 1,234.0</td>
<td>e.g. 1,234.0</td>
</tr>
<tr>
<td>amountString</td>
<td>str</td>
<td>ex. "$ 1,234"</td>
<td>e.g. "$ 1,234"</td>
</tr>
<tr>
<td>currency</td>
<td>str</td>
<td><a href="https://en.wikipedia.org/wiki/ISO_4217">ISO 4217 currency codes</a> (ex. "USD")</td>
<td><a href="https://en.wikipedia.org/wiki/ISO_4217">ISO 4217 currency codes</a> (e.g. "USD")</td>
</tr>
<tr>
<td>bgColor</td>
@@ -193,7 +202,7 @@ Structure of author object.
<tr>
<td>channelId</td>
<td>str</td>
<td></td>
<td>*chatter's channel ID.</td>
</tr>
<tr>
<td>channelUrl</td>

View File

@@ -2,7 +2,7 @@
pytchat is a python library for fetching youtube live chat without using yt api, Selenium, or BeautifulSoup.
"""
__copyright__ = 'Copyright (C) 2019 taizan-hokuto'
__version__ = '0.0.3.0'
__version__ = '0.0.3.8'
__license__ = 'MIT'
__author__ = 'taizan-hokuto'
__author_email__ = '55448286+taizan-hokuto@users.noreply.github.com'
@@ -18,5 +18,6 @@ from .api import (
ChatProcessor,
CompatibleProcessor,
SimpleDisplayProcessor,
JsonfileArchiveProcessor
JsonfileArchiveProcessor,
SpeedCalculator
)

View File

@@ -7,4 +7,4 @@ from .processors.default.processor import DefaultProcessor
from .processors.compatible.processor import CompatibleProcessor
from .processors.simple_display_processor import SimpleDisplayProcessor
from .processors.jsonfile_archive_processor import JsonfileArchiveProcessor
from .processors.speed_calculator import SpeedCalculator

View File

@@ -1,4 +1,4 @@
import logging
LOGGER_MODE = logging.DEBUG
LOGGER_MODE = None
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'}

View File

@@ -3,7 +3,6 @@ import datetime
import json
import random
import signal
import threading
import time
import traceback
import urllib.parse
@@ -123,7 +122,7 @@ class LiveChatAsync:
async def _startlisten(self):
"""最初のcontinuationパラメータを取得し、
_listenループ開始する
_listenループのタスクを作成し開始する
"""
initial_continuation = await self._get_initial_continuation()
if initial_continuation is None:
@@ -287,12 +286,3 @@ class LiveChatAsync:
await asyncio.gather(*tasks,return_exceptions=True)
loop = asyncio.get_event_loop()
loop.stop()

View File

@@ -21,14 +21,19 @@ logger = mylogger.get_logger(__name__,mode=config.LOGGER_MODE)
MAX_RETRY = 10
headers = config.headers
class ReplayChatAsync:
''' aiohttpを利用してYouTubeのライブ配信のチャットデータを取得する
'''asyncio(aiohttp)を利用してYouTubeのチャットデータを取得する
Parameter
---------
video_id : str
動画ID
seektime : int
リプレイするチャットデータの開始時間(秒)
processor : ChatProcessor
チャットデータを加工するオブジェクト
@@ -46,6 +51,9 @@ class ReplayChatAsync:
done_callback : func
listener終了時に呼び出すコールバック。
exception_handler : func
例外を処理する関数
direct_mode : bool
Trueの場合、bufferを使わずにcallbackを呼ぶ。
Trueの場合、callbackの設定が必須
@@ -53,26 +61,23 @@ class ReplayChatAsync:
Attributes
---------
_executor : ThreadPoolExecutor
チャットデータ取得ループ_listen用のスレッド
_is_alive : bool
チャット取得を終了したか
チャット取得を停止するためのフラグ
'''
_setup_finished = False
def __init__(self, video_id,
seektime =0,
seektime = 0,
processor = DefaultProcessor(),
buffer = Buffer(maxsize = 20),
buffer = None,
interruptable = True,
callback = None,
done_callback = None,
exception_handler = None,
direct_mode = False):
self.video_id = video_id
self.seektime= seektime
self.seektime = seektime
self.processor = processor
self._buffer = buffer
self._callback = callback
@@ -151,8 +156,8 @@ class ReplayChatAsync:
async def _listen(self, continuation):
''' continuationに紐付いたチャットデータを取得し
にチャットデータを格納、
次のcontinuaitonを取得してループする
Bufferにチャットデータを格納、
次のcontinuaitonを取得してループする
Parameter
---------
@@ -163,10 +168,10 @@ class ReplayChatAsync:
async with aiohttp.ClientSession() as session:
while(continuation and self._is_alive):
if self._pauser.empty():
#pauseが呼ばれて_pauserが空状態のときは一時停止する
#pause
await self._pauser.get()
#resumeが呼ばれて_pauserにitemが入ったら再開する
#直後に_pauserにitem(None)を入れてブロックを防ぐ
#resume
#prohibit from blocking by putting None into _pauser.
self._pauser.put_nowait(None)
livechat_json = (await
self._get_livechat_json(continuation, session, headers)
@@ -186,11 +191,10 @@ class ReplayChatAsync:
else:
await self._buffer.put(chat_component)
diff_time = timeout - (time.time()-time_mark)
if diff_time < 0 : diff_time=0
await asyncio.sleep(diff_time)
continuation = metadata.get('continuation')
except ChatParseException as e:
logger.error(f"{str(e)}動画ID:\"{self.video_id}\"")
logger.info(f"{str(e)}video_id:\"{self.video_id}\"")
return
except (TypeError , json.JSONDecodeError) :
logger.error(f"{traceback.format_exc(limit = -1)}")

View File

@@ -57,7 +57,7 @@ class LiveChat:
チャットデータ取得ループ_listen用のスレッド
_is_alive : bool
チャット取得を終了したか
チャット取得を停止するためのフラグ
'''
_setup_finished = False
@@ -142,7 +142,7 @@ class LiveChat:
def _listen(self, continuation):
''' continuationに紐付いたチャットデータを取得し
にチャットデータを格納、
BUfferにチャットデータを格納、
次のcontinuaitonを取得してループする
Parameter
@@ -157,7 +157,6 @@ class LiveChat:
self._get_livechat_json(continuation, session, headers)
)
metadata, chatdata = self._parser.parse( livechat_json )
#チャットデータを含むコンポーネントを組み立ててbufferに投入する
timeout = metadata['timeoutMs']/1000
chat_component = {
"video_id" : self.video_id,
@@ -171,16 +170,12 @@ class LiveChat:
)
else:
self._buffer.put(chat_component)
#次のchatを取得するまでsleepする
diff_time = timeout - (time.time()-time_mark)
if diff_time < 0 : diff_time=0
time.sleep(diff_time)
#次のチャットデータのcontinuationパラメータを取り出す。
continuation = metadata.get('continuation')
#whileループ先頭に戻る
except ChatParseException as e:
logger.error(f"{str(e)}動画ID:\"{self.video_id}\"")
logger.info(f"{str(e)}video_id:\"{self.video_id}\"")
return
except (TypeError , json.JSONDecodeError) :
logger.error(f"{traceback.format_exc(limit = -1)}")

View File

@@ -30,6 +30,9 @@ class ReplayChat:
video_id : str
動画ID
seektime : int
リプレイするチャットデータの開始時間(秒)
processor : ChatProcessor
チャットデータを加工するオブジェクト
@@ -65,7 +68,7 @@ class ReplayChat:
#チャット監視中のListenerのリスト
_listeners= []
def __init__(self, video_id,
seektime =0,
seektime = 0,
processor = DefaultProcessor(),
buffer = Buffer(maxsize = 20),
interruptable = True,
@@ -74,7 +77,7 @@ class ReplayChat:
direct_mode = False
):
self.video_id = video_id
self.seektime= seektime
self.seektime = seektime
self.processor = processor
self._buffer = buffer
self._callback = callback
@@ -159,16 +162,15 @@ class ReplayChat:
with requests.Session() as session:
while(continuation and self._is_alive):
if self._pauser.empty():
#pauseが呼ばれて_pauserが空状態のときは一時停止する
#pause
self._pauser.get()
#resumeが呼ばれて_pauserにitemが入ったら再開する
#直後に_pauserにitem(None)を入れてブロックを防ぐ
#resume
#prohibit from blocking by putting None into _pauser.
self._pauser.put_nowait(None)
livechat_json = (
self._get_livechat_json(continuation, session, headers)
)
metadata, chatdata = self._parser.parse( livechat_json )
#チャットデータを含むコンポーネントを組み立ててbufferに投入する
timeout = metadata['timeoutMs']/1000
chat_component = {
"video_id" : self.video_id,

View File

@@ -17,7 +17,7 @@ def get_logger(modname,mode=logging.DEBUG):
logger.addHandler(handler1)
#create handler2 for recording log file
if mode <= logging.DEBUG:
handler2 = logging.FileHandler(filename="log.txt")
handler2 = logging.FileHandler(filename="log.txt", encoding='utf-8')
handler2.setLevel(logging.ERROR)
handler2.setFormatter(my_formatter)

View File

@@ -1,3 +1,9 @@
"""
pytchat.parser.live
~~~~~~~~~~~~~~~~~~~
This module is parser of live chat JSON.
"""
import json
from .. import config
from .. import mylogger
@@ -12,6 +18,27 @@ logger = mylogger.get_logger(__name__,mode=config.LOGGER_MODE)
class Parser:
def parse(self, jsn):
"""
このparse関数はLiveChat._listen() 関数から定期的に呼び出される。
引数jsnはYoutubeから取得したチャットデータの生JSONであり、
このparse関数によって与えられたJSONを以下に分割して返す。
+ timeout (次のチャットデータ取得までのインターバル)
+ chat dataチャットデータ本体
+ continuation (次のチャットデータ取得に必要となるパラメータ).
Parameter
----------
+ jsn : dict
+ Youtubeから取得したチャットデータのJSONオブジェクト。
pythonの辞書形式に変換済みの状態で渡される
Returns
-------
+ metadata : dict
+ チャットデータに付随するメタデータ。timeout、 動画ID、continuationパラメータで構成される。
+ chatdata : list[dict]
+ チャットデータ本体のリスト。
"""
if jsn is None:
return {'timeoutMs':0,'continuation':None},[]
if jsn['response']['responseContext'].get('errors'):

View File

@@ -12,6 +12,31 @@ logger = mylogger.get_logger(__name__,mode=config.LOGGER_MODE)
class Parser:
def parse(self, jsn):
"""
このparse関数はReplayChat._listen() 関数から定期的に呼び出される。
引数jsnはYoutubeから取得したアーカイブ済みチャットデータの生JSONであり、
このparse関数によって与えられたJSONを以下に分割して返す。
+ timeout (次のチャットデータ取得までのインターバル)
+ chat dataチャットデータ本体
+ continuation (次のチャットデータ取得に必要となるパラメータ).
ライブ配信のチャットとアーカイブ済み動画のチャットは構造が若干異なっているが、
ライブチャットと同じデータ形式に変換することにより、
同じprocessorでライブとリプレイどちらでも利用できるようにしている。
Parameter
----------
+ jsn : dict
+ Youtubeから取得したチャットデータのJSONオブジェクト。
pythonの辞書形式に変換済みの状態で渡される
Returns
-------
+ metadata : dict
+ チャットデータに付随するメタデータ。timeout、 動画ID、continuationパラメータで構成される。
+ chatdata : list[dict]
+ チャットデータ本体のリスト。
"""
if jsn is None:
return {'timeoutMs':0,'continuation':None},[]
if jsn['response']['responseContext'].get('errors'):
@@ -36,9 +61,9 @@ class Parser:
raise NoContentsException('チャットデータを取得できませんでした。')
interval = self.get_interval(actions)
metadata.setdefault("timeoutMs",interval)
chatdata = []
for action in actions:
chatdata.append(action["replayChatItemAction"]["actions"][0])
"""アーカイブ済みチャットはライブチャットと構造が異なっているため、以下の行により
ライブチャットと同じ形式にそろえる"""
chatdata = [action["replayChatItemAction"]["actions"][0] for action in actions]
return metadata, chatdata
def get_interval(self, actions: list):

View File

@@ -10,14 +10,14 @@ class ChatProcessor:
Parameter
----------
chat_components: [LIST:component]
chat_components: List[component]
component : dict {
"video_id" : str
動画ID
"timeout" : int
次のチャットの再読み込みまでの時間(秒)
"chatdata" : list<object>
チャットデータactionsのリスト
"chatdata" : List[dict]
チャットデータのリスト
}
'''
pass

View File

@@ -4,11 +4,12 @@ from .renderer.textmessage import LiveChatTextMessageRenderer
from .renderer.paidmessage import LiveChatPaidMessageRenderer
from .renderer.paidsticker import LiveChatPaidStickerRenderer
from .renderer.legacypaid import LiveChatLegacyPaidMessageRenderer
from .. chat_processor import ChatProcessor
from ... import mylogger
from ... import config
logger = mylogger.get_logger(__name__,mode=config.LOGGER_MODE)
class CompatibleProcessor:
class CompatibleProcessor(ChatProcessor):
def process(self, chat_components: list):

View File

@@ -4,7 +4,10 @@ from .renderer.textmessage import LiveChatTextMessageRenderer
from .renderer.paidmessage import LiveChatPaidMessageRenderer
from .renderer.paidsticker import LiveChatPaidStickerRenderer
from .renderer.legacypaid import LiveChatLegacyPaidMessageRenderer
from .. chat_processor import ChatProcessor
from ... import config
from ... import mylogger
logger = mylogger.get_logger(__name__,mode=config.LOGGER_MODE)
class Chatdata:
def __init__(self,chatlist:list, timeout:float):
@@ -23,7 +26,7 @@ class Chatdata:
return
await asyncio.sleep(self.interval/len(self.items))
class DefaultProcessor:
class DefaultProcessor(ChatProcessor):
def process(self, chat_components: list):
chatlist = []
@@ -40,32 +43,31 @@ class DefaultProcessor:
if action.get('addChatItemAction') is None: continue
if action['addChatItemAction'].get('item') is None: continue
chat = self.parse(action)
chat = self._parse(action)
if chat:
chatlist.append(chat)
return Chatdata(chatlist, float(timeout))
def parse(self, sitem):
def _parse(self, sitem):
action = sitem.get("addChatItemAction")
if action:
item = action.get("item")
if item is None: return None
try:
renderer = self.get_renderer(item)
renderer = self._get_renderer(item)
if renderer == None:
return None
renderer.get_snippet()
renderer.get_authordetails()
except (KeyError,TypeError,AttributeError) as e:
print(f"------{str(type(e))}-{str(e)}----------")
print(sitem)
logger.error(f"{str(type(e))}-{str(e)} sitem:{str(sitem)}")
return None
return renderer
def get_renderer(self, item):
def _get_renderer(self, item):
if item.get("liveChatTextMessageRenderer"):
renderer = LiveChatTextMessageRenderer(item)
elif item.get("liveChatPaidMessageRenderer"):

View File

@@ -15,11 +15,12 @@ class BaseRenderer:
self.timestamp = int(timestampUsec/1000)
tst = self.renderer.get("timestampText")
if tst:
self.timestampText = tst.get("simpleText")
self.elapsedTime = tst.get("simpleText")
else:
self.timestampText = ""
self.elapsedTime = ""
self.datetime = self.get_datetime(timestampUsec)
self.message = self.get_message(self.renderer)
self.messageEx = self.get_message_ex(self.renderer)
self.id = self.renderer.get('id')
self.amountValue= 0.0
self.amountString = ""
@@ -54,6 +55,19 @@ class BaseRenderer:
message += r.get('text','')
return message
def get_message_ex(self,renderer):
message = []
if renderer.get("message"):
runs=renderer["message"].get("runs")
if runs:
for r in runs:
if r:
if r.get('emoji'):
message.append(r['emoji']['image']['thumbnails'][1].get('url'))
else:
message.append(r.get('text',''))
return message
def get_badges(self,renderer):
isVerified = False
isChatOwner = False

View File

@@ -1,12 +1,42 @@
import re
from . import currency
from .paidmessage import LiveChatPaidMessageRenderer
from .base import BaseRenderer
superchat_regex = re.compile(r"^(\D*)(\d{1,3}(,\d{3})*(\.\d*)*\b)$")
class LiveChatPaidStickerRenderer(LiveChatPaidMessageRenderer):
class LiveChatPaidStickerRenderer(BaseRenderer):
def __init__(self, item):
super().__init__(item, "superSticker")
def get_snippet(self):
super().get_snippet()
self.author.name = self.renderer["authorName"]["simpleText"]
amountDisplayString, symbol, amount =(
self.get_amountdata(self.renderer)
)
self.message = ""
self.amountValue = amount
self.amountString = amountDisplayString
self.currency = currency.symbols[symbol]["fxtext"] if currency.symbols.get(symbol) else symbol
self.bgColor = self.renderer.get("moneyChipBackgroundColor", 0)
self.sticker = "https:"+self.renderer["sticker"]["thumbnails"][0]["url"]
def get_amountdata(self,renderer):
amountDisplayString = renderer["purchaseAmountText"]["simpleText"]
m = superchat_regex.search(amountDisplayString)
if m:
symbol = m.group(1)
amount = float(m.group(2).replace(',',''))
else:
symbol = ""
amount = 0.0
return amountDisplayString, symbol, amount

View File

@@ -0,0 +1,204 @@
"""
speedmeter.py
チャットの勢いを算出するChatProcessor
Calculate speed of chat.
"""
import calendar, datetime, pytz
from .chat_processor import ChatProcessor
class RingQueue:
"""
リング型キュー
Attributes
----------
items : list
格納されているアイテムのリスト。
first_pos : int
キュー内の一番古いアイテムを示すリストのインデックス。
last_pos : int
キュー内の一番新しいアイテムを示すリストのインデックス。
mergin : boolean
キュー内に余裕があるか。キュー内のアイテム個数が、キューの最大個数未満であればTrue。
"""
def __init__(self, capacity):
"""
コンストラクタ
Parameter
----------
capacity:このキューに格納するアイテムの最大個数。
格納時に最大個数を超える場合は一番古いアイテムから
上書きする。
"""
if capacity <= 0:
raise ValueError
self.items = list()
self.capacity = capacity
self.first_pos = 0
self.last_pos = 0
self.mergin = True
def put(self, item):
"""
引数itemに指定されたアイテムをこのキューに格納する。
キューの最大個数を超える場合は、一番古いアイテムの位置に上書きする。
Parameter
----------
item:格納するアイテム
"""
if self.mergin:
self.items.append(item)
self.last_pos = len(self.items)-1
if self.last_pos == self.capacity-1:
self.mergin = False
return
self.last_pos += 1
if self.last_pos > self.capacity-1:
self.last_pos = 0
self.items[self.last_pos] = item
self.first_pos += 1
if self.first_pos > self.capacity-1:
self.first_pos = 0
def get(self):
"""
キュー内の一番古いアイテムへの参照を返す
(アイテムは削除しない)
Return
----------
キュー内の一番古いアイテムへの参照
"""
return self.items[self.first_pos]
def item_count(self):
return len(self.items)
class SpeedCalculator(ChatProcessor, RingQueue):
"""
チャットの勢いを計算する。
一定期間のチャットデータのうち、最初のチャットの投稿時刻と
最後のチャットの投稿時刻の差を、チャット数で割り返し
1分あたりの速度に換算する。
Parameter
----------
capacity : int
RingQueueに格納するチャット勢い算出用データの最大数
"""
def __init__(self, capacity = 10):
super().__init__(capacity)
self.speed = 0
def process(self, chat_components: list):
chatdata = []
if chat_components:
for component in chat_components:
if component.get("chatdata"):
chatdata.extend(component.get("chatdata"))
self._put_chatdata(chatdata)
self.speed = self._calc_speed()
return self.speed
def _calc_speed(self):
"""
RingQueue内のチャット勢い算出用データリストを元に、
チャット速度を計算して返す
Return
---------------------------
チャット速度(1分間で換算したチャット数)
"""
try:
#キュー内の総チャット数
total = sum(item['chat_count'] for item in self.items)
#キュー内の最初と最後のチャットの時間差
duration = (self.items[self.last_pos]['endtime']
- self.items[self.first_pos]['starttime'])
if duration != 0:
return int(total*60/duration)
return 0
except IndexError:
return 0
def _put_chatdata(self, actions):
"""
チャットデータからタイムスタンプを読み取り、勢い測定用のデータを組み立て、
RingQueueに投入する。
200円以上のスパチャはtickerとmessageの2つのデータが生成されるが、
tickerの方は時刻データの場所が異なることを利用し、勢いの集計から除外している。
Parameter
---------
actions : List[dict]
チャットデータ(addChatItemAction) のリスト
"""
def _put_emptydata():
'''
チャットデータがない場合に空のデータをキューに投入する。
'''
timestamp_now = calendar.timegm(datetime.datetime.
now(pytz.utc).utctimetuple())
self.put({
'chat_count':0,
'starttime':int(timestamp_now),
'endtime':int(timestamp_now)
})
def _get_timestamp(action :dict):
"""
チャットデータから時刻データを取り出す。
"""
try:
item = action['addChatItemAction']['item']
timestamp = int(item[list(item.keys())[0]]['timestampUsec'])
except (KeyError,TypeError):
return None
return timestamp
if actions is None or len(actions)==0:
_put_emptydata()
return
#actions内の時刻データを持つチャットデータの数
counter=0
#actions内の最初のチャットデータの時刻
starttime= None
#actions内の最後のチャットデータの時刻
endtime=None
for action in actions:
#チャットデータからtimestampUsecを読み取る
gettime = _get_timestamp(action)
#時刻のないデータだった場合は次の行のデータで読み取り試行
if gettime is None:
continue
#最初に有効な時刻を持つデータのtimestampをstarttimeに設定
if starttime is None:
starttime = gettime
#最後のtimestampを設定(途中で時刻のないデータの場合もあるので上書きしていく)
endtime = gettime
#チャットの数をインクリメント
counter += 1
#チャット速度用のデータをRingQueueに送る
if starttime is None or endtime is None:
_put_emptydata()
return
self.put({
'chat_count':counter,
'starttime':int(starttime/1000000),
'endtime':int(endtime/1000000)
})

View File

@@ -0,0 +1,68 @@
import json
import pytest
import asyncio,aiohttp
from pytchat.parser.live import Parser
from pytchat.processors.compatible.processor import CompatibleProcessor
from pytchat.exceptions import (
NoLivechatRendererException,NoYtinitialdataException,
ResponseContextError, NoContentsException)
from pytchat.processors.speed_calculator import SpeedCalculator
parser = Parser()
def test_speed_1(mocker):
'''test speed calculation with normal json.
test json has 15 chatdata, duration is 30 seconds,
so the speed of chatdata is 30 chats/minute.
'''
processor = SpeedCalculator(capacity=30)
_json = _open_file("tests/testdata/speed/speedtest_normal.json")
_, chatdata = parser.parse(json.loads(_json))
data = {
"video_id" : "",
"timeout" : 10,
"chatdata" : chatdata
}
ret = processor.process([data])
assert 30 == ret
def test_speed_2(mocker):
'''test speed calculation with no valid chat data.
'''
processor = SpeedCalculator(capacity=30)
_json = _open_file("tests/testdata/speed/speedtest_undefined.json")
_, chatdata = parser.parse(json.loads(_json))
data = {
"video_id" : "",
"timeout" : 10,
"chatdata" : chatdata
}
ret = processor.process([data])
assert 0 == ret
def test_speed_3(mocker):
'''test speed calculation with empty data.
'''
processor = SpeedCalculator(capacity=30)
_json = _open_file("tests/testdata/speed/speedtest_empty.json")
_, chatdata = parser.parse(json.loads(_json))
data = {
"video_id" : "",
"timeout" : 10,
"chatdata" : chatdata
}
ret = processor.process([data])
assert 0 == ret
def _open_file(path):
with open(path,mode ='r',encoding = 'utf-8') as f:
return f.read()

164
tests/testdata/chat.json vendored Normal file
View File

@@ -0,0 +1,164 @@
{
"timing": {
"info": {
"st": 164
}
},
"csn": "",
"response": {
"responseContext": {
"serviceTrackingParams": [{
"service": "CSI",
"params": [{
"key": "GetLiveChat_rid",
"value": ""
}, {
"key": "c",
"value": "WEB"
}, {
"key": "cver",
"value": "2.20191219.03.01"
}, {
"key": "yt_li",
"value": "0"
}]
}, {
"service": "GFEEDBACK",
"params": [{
"key": "e",
"value": ""
}, {
"key": "logged_in",
"value": "0"
}]
}, {
"service": "GUIDED_HELP",
"params": [{
"key": "logged_in",
"value": "0"
}]
}, {
"service": "ECATCHER",
"params": [{
"key": "client.name",
"value": "WEB"
}, {
"key": "client.version",
"value": "2.2"
}, {
"key": "innertube.build.changelist",
"value": "228"
}, {
"key": "innertube.build.experiments.source_version",
"value": "2858"
}, {
"key": "innertube.build.label",
"value": "youtube.ytfe.innertube_"
}, {
"key": "innertube.build.timestamp",
"value": "154"
}, {
"key": "innertube.build.variants.checksum",
"value": "e"
}, {
"key": "innertube.run.job",
"value": "ytfe-innertube-replica-only.ytfe"
}]
}],
"webResponseContextExtensionData": {
"ytConfigData": {
"csn": "ADw",
"visitorData": "%3D%3D"
}
}
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [{
"timedContinuationData": {
"timeoutMs": 10000,
"continuation": "continuation"
}
}],
"actions": [{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"message": {
"runs": [{
"text": "message"
}]
},
"authorName": {
"simpleText": "authorName"
},
"authorPhoto": {
"thumbnails": [{
"url": "https://yt3.ggpht.com/photo.jpg",
"width": 32,
"height": 32
}, {
"url": "https://yt3.ggpht.com/photo.jpg",
"width": 64,
"height": 64
}]
},
"contextMenuEndpoint": {
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "params"
}
},
"id": "id",
"timestampUsec": "1576851922945411",
"authorBadges": [{
"liveChatAuthorBadgeRenderer": {
"customThumbnail": {
"thumbnails": [{
"url": "https://yt3.ggpht.com/photo.jpg"
}, {
"url": "https://yt3.ggpht.com/photo.jpg"
}]
},
"tooltip": "メンバー6 か月)",
"accessibility": {
"accessibilityData": {
"label": "メンバー6 か月)"
}
}
}
}],
"authorExternalChannelId": "UC",
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
}
}
},
"clientId": "00000000000000000000"
}
}
]}
},
"xsrf_token": "xsrf_token",
"url": "/live_chat/get_live_chat?continuation=0",
"endpoint": {
"commandMetadata": {
"webCommandMetadata": {
"url": "/live_chat/get_live_chat?continuation=0",
"rootVe": 0
}
},
"urlEndpoint": {
"url": "/live_chat/get_live_chat?continuation=0"
}
}
}
}

View File

@@ -0,0 +1,24 @@
{
"timing": {
"info": {
"st": 164
}
},
"csn": "",
"response": {
"responseContext": {
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [{
"timedContinuationData": {
"timeoutMs": 10000,
"continuation": "continuation"
}
}]
}
}
}
}

View File

@@ -0,0 +1,188 @@
{
"timing": {
"info": {
"st": 164
}
},
"csn": "",
"response": {
"responseContext": {
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [{
"timedContinuationData": {
"timeoutMs": 10000,
"continuation": "continuation"
}
}],
"actions": [{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000000000000"
}
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"timestampUsec": "1500000030000000"
}
}
}
}
]}
}
}
}

View File

@@ -0,0 +1,42 @@
{
"timing": {
"info": {
"st": 164
}
},
"csn": "",
"response": {
"responseContext": {
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [{
"timedContinuationData": {
"timeoutMs": 10000,
"continuation": "continuation"
}
}],
"actions": [{
"addChatItemAction": {
"liveChatPlaceholderItemRenderer": {
"id": "",
"timestampUsec": "1500000000000000"
}
}
},
{
"addChatItemAction": {
"item": {
"liveChatPlaceholderItemRenderer": {
"id": "",
"timestampUsec": "1500000030000000"
}
}
}
}
]}
}
}
}