Compare commits

...

29 Commits

Author SHA1 Message Date
taizan-hokuto
1c817b6476 Merge branch 'release/v0.0.7.2' 2020-05-22 02:39:53 +09:00
taizan-hokuto
18b88200a8 Increment version 2020-05-22 02:29:41 +09:00
taizan-hokuto
c95d70a232 Merge branch 'hotfix/#7_cli_index_outof_range' 2020-05-22 02:28:28 +09:00
taizan-hokuto
7640586591 Merge branch 'master' into develop 2020-05-22 02:28:28 +09:00
taizan-hokuto
f7ec14e166 Fix for #7 2020-05-22 02:27:52 +09:00
taizan-hokuto
a4dacdb7d7 Merge tag 'v0.0.7.1' into develop
v0.0.7.1
2020-05-06 01:24:55 +09:00
taizan-hokuto
785a82b618 Merge branch 'release/v0.0.7.1' 2020-05-06 01:24:54 +09:00
taizan-hokuto
faf886eebd Increment version 2020-05-06 01:24:30 +09:00
taizan-hokuto
8a627414cb Merge tag 'sponsor_text' into develop 2020-05-06 01:23:37 +09:00
taizan-hokuto
d14262cbcb Merge branch 'hotfix/sponsor_text' 2020-05-06 01:23:37 +09:00
taizan-hokuto
da7c694dfb Modify parsing membership 2020-05-06 01:23:19 +09:00
taizan-hokuto
9aa35b9756 Merge tag 'v0.0.7' into develop
v0.0.7
2020-05-05 22:59:16 +09:00
taizan-hokuto
f0a1a509a0 Merge branch 'release/v0.0.7' 2020-05-05 22:59:16 +09:00
taizan-hokuto
5ebca605ac Increment version 2020-05-05 22:58:29 +09:00
taizan-hokuto
3826b32ab9 Merge tag 'membership_renderer' into develop 2020-05-05 22:51:16 +09:00
taizan-hokuto
a46c82d3c0 Merge branch 'hotfix/membership_renderer' 2020-05-05 22:51:16 +09:00
taizan-hokuto
206d052907 Modify parsing membership 2020-05-05 22:47:12 +09:00
taizan-hokuto
141d7a9299 Merge tag 'termination' into develop 2020-05-05 21:18:46 +09:00
taizan-hokuto
04457eaa5c Merge branch 'hotfix/termination' 2020-05-05 21:18:46 +09:00
taizan-hokuto
bd32c75833 Modify termination 2020-05-05 21:16:06 +09:00
taizan-hokuto
84bae4ad2a Modify bytes combination 2020-04-18 00:55:56 +09:00
taizan-hokuto
d72608bf0a Merge tag 'json_decode_error' into develop
v0.0.6.6
2020-03-14 09:43:37 +09:00
taizan-hokuto
3243d69d7a Merge branch 'hotfix/json_decode_error' 2020-03-14 09:43:37 +09:00
taizan-hokuto
6e1b735ebc Increment version 2020-03-14 09:42:53 +09:00
taizan-hokuto
c54481dad5 Add header html and show progress 2020-03-14 09:26:28 +09:00
taizan-hokuto
78604c84d4 Fix testdata path separator 2020-03-14 08:16:19 +09:00
taizan-hokuto
21d93613a2 Handling JSONDecodeError 2020-03-14 08:00:31 +09:00
taizan-hokuto
56bf721330 Merge tag 'argparse' into develop
v0.0.6.5
2020-03-10 01:58:25 +09:00
taizan-hokuto
725af25d81 Merge tag 'v0.0.6.4' into develop
v0.0.6.4
2020-03-08 23:43:01 +09:00
18 changed files with 2240 additions and 266 deletions

View File

@@ -7,10 +7,10 @@ pytchat is a python library for fetching youtube live chat.
pytchat is a python library for fetching youtube live chat pytchat is a python library for fetching youtube live chat
without using youtube api, Selenium or BeautifulSoup. without using youtube api, Selenium or BeautifulSoup.
pytchatはAPIを使わずにYouTubeチャットを取得するための軽量pythonライブラリです。 pytchatはAPIを使わずにYouTubeチャットを取得するためのpythonライブラリです。
Other features: Other features:
+ Customizable chat data processors including youtube api compatible one. + Customizable [chat data processors](https://github.com/taizan-hokuto/pytchat/wiki/ChatProcessor) including youtube api compatible one.
+ Available on asyncio context. + Available on asyncio context.
+ Quick fetching of initial chat data by generating continuation params + Quick fetching of initial chat data by generating continuation params
instead of web scraping. instead of web scraping.

View File

@@ -2,7 +2,7 @@
pytchat is a python library for fetching youtube live chat without using yt api, Selenium, or BeautifulSoup. pytchat is a python library for fetching youtube live chat without using yt api, Selenium, or BeautifulSoup.
""" """
__copyright__ = 'Copyright (C) 2019 taizan-hokuto' __copyright__ = 'Copyright (C) 2019 taizan-hokuto'
__version__ = '0.0.6.5' __version__ = '0.0.7.2'
__license__ = 'MIT' __license__ = 'MIT'
__author__ = 'taizan-hokuto' __author__ = 'taizan-hokuto'
__author_email__ = '55448286+taizan-hokuto@users.noreply.github.com' __author_email__ = '55448286+taizan-hokuto@users.noreply.github.com'

View File

@@ -22,9 +22,10 @@ def main():
# Arguments # Arguments
parser = argparse.ArgumentParser(description=f'pytchat v{__version__}') parser = argparse.ArgumentParser(description=f'pytchat v{__version__}')
parser.add_argument('-v', f'--{Arguments.Name.VIDEO}', type=str, parser.add_argument('-v', f'--{Arguments.Name.VIDEO}', type=str,
help='Video IDs separated by commas without space') help='Video IDs separated by commas without space.\n'
'If ID starts with a hyphen (-), enclose the ID in square brackets.')
parser.add_argument('-o', f'--{Arguments.Name.OUTPUT}', type=str, parser.add_argument('-o', f'--{Arguments.Name.OUTPUT}', type=str,
help='Output directory (end with "/")', default='./') help='Output directory (end with "/"). default="./"', default='./')
parser.add_argument(f'--{Arguments.Name.VERSION}', action='store_true', parser.add_argument(f'--{Arguments.Name.VERSION}', action='store_true',
help='Settings version') help='Settings version')
Arguments(parser.parse_args().__dict__) Arguments(parser.parse_args().__dict__)
@@ -43,11 +44,17 @@ def main():
f" video_id: {video_id}\n" f" video_id: {video_id}\n"
f" channel: {info.get_channel_name()}\n" f" channel: {info.get_channel_name()}\n"
f" title: {info.get_title()}") f" title: {info.get_title()}")
path = Path(Arguments().output+video_id+'.html')
print(f"output path: {path.resolve()}")
Extractor(video_id, Extractor(video_id,
processor = HTMLArchiver(Arguments().output+video_id+'.html') processor = HTMLArchiver(Arguments().output+video_id+'.html'),
callback = _disp_progress
).extract() ).extract()
print("Extraction end.\n") print("\nExtraction end.\n")
except (InvalidVideoIdException, NoContentsException) as e: except (InvalidVideoIdException, NoContentsException) as e:
print(e) print(e)
return return
parser.print_help() parser.print_help()
def _disp_progress(a,b):
print('.',end="",flush=True)

View File

@@ -72,8 +72,6 @@ class LiveChat:
''' '''
_setup_finished = False _setup_finished = False
#チャット監視中のListenerのリスト
_listeners = []
def __init__(self, video_id, def __init__(self, video_id,
seektime=0, seektime=0,
@@ -103,19 +101,13 @@ class LiveChat:
self._parser = Parser(is_replay=self._is_replay) self._parser = Parser(is_replay=self._is_replay)
self._pauser = Queue() self._pauser = Queue()
self._pauser.put_nowait(None) self._pauser.put_nowait(None)
self._setup()
self._first_fetch = True self._first_fetch = True
self._fetch_url = "live_chat/get_live_chat?continuation=" self._fetch_url = "live_chat/get_live_chat?continuation="
self._topchat_only = topchat_only self._topchat_only = topchat_only
self._logger = logger self._logger = logger
LiveChat._logger = logger
if not LiveChat._setup_finished:
LiveChat._setup_finished = True
if interruptable: if interruptable:
signal.signal(signal.SIGINT, (lambda a, b: signal.signal(signal.SIGINT, lambda a, b: self.terminate())
(LiveChat.shutdown(None,signal.SIGINT,b)) self._setup()
))
LiveChat._listeners.append(self)
def _setup(self): def _setup(self):
# direct modeがTrueでcallback未設定の場合例外発生。 # direct modeがTrueでcallback未設定の場合例外発生。
@@ -174,7 +166,8 @@ class LiveChat:
} }
time_mark = time.time() time_mark = time.time()
if self._direct_mode: if self._direct_mode:
processed_chat = self.processor.process([chat_component]) processed_chat = self.processor.process(
[chat_component])
if isinstance(processed_chat, tuple): if isinstance(processed_chat, tuple):
self._callback(*processed_chat) self._callback(*processed_chat)
else: else:
@@ -319,14 +312,7 @@ class LiveChat:
''' '''
Listenerを終了する。 Listenerを終了する。
''' '''
if self.is_alive():
self._is_alive = False self._is_alive = False
if self._direct_mode == False: self._buffer.put({})
#bufferにダミーオブジェクトを入れてis_alive()を判定させる self._logger.info(f'[{self.video_id}]終了しました')
self._buffer.put({'chatdata':'','timeout':0})
self._logger.info(f'[{self.video_id}]finished.')
@classmethod
def shutdown(cls, event, sig = None, handler=None):
cls._logger.debug("shutdown...")
for t in LiveChat._listeners:
t._is_alive = False

View File

@@ -1,46 +1,52 @@
class ChatParseException(Exception): class ChatParseException(Exception):
''' '''
チャットデータをパースするライブラリが投げる例外の基底クラス Base exception thrown by the parser
''' '''
pass pass
class NoYtinitialdataException(ChatParseException): class NoYtinitialdataException(ChatParseException):
''' '''
配信ページ内にチャットデータurlが見つからないときに投げる例外 Thrown when the video is not found.
''' '''
pass pass
class ResponseContextError(ChatParseException): class ResponseContextError(ChatParseException):
''' '''
配信ページでチャットデータ無効の時に投げる例外 Thrown when chat data is invalid.
''' '''
pass pass
class NoLivechatRendererException(ChatParseException): class NoLivechatRendererException(ChatParseException):
''' '''
チャットデータのJSON中にlivechatRendererがない時に投げる例外 Thrown when livechatRenderer is missing in JSON.
''' '''
pass pass
class NoContentsException(ChatParseException): class NoContentsException(ChatParseException):
''' '''
チャットデータのJSON中にContinuationContentsがない時に投げる例外 Thrown when ContinuationContents is missing in JSON.
''' '''
pass pass
class NoContinuationsException(ChatParseException): class NoContinuationsException(ChatParseException):
''' '''
チャットデータのContinuationContents中にcontinuationがない時に投げる例外 Thrown when continuation is missing in ContinuationContents.
''' '''
pass pass
class IllegalFunctionCall(Exception): class IllegalFunctionCall(Exception):
''' '''
set_callback()を実行済みにもかかわらず Thrown when get () is called even though
get()を呼び出した場合の例外 set_callback () has been executed.
''' '''
pass pass
class InvalidVideoIdException(Exception): class InvalidVideoIdException(Exception):
'''
Thrown when the video_id is not exist (VideoInfo).
'''
pass
class UnknownConnectionError(Exception):
pass pass

View File

@@ -12,6 +12,7 @@ Author: taizan-hokuto (2019) @taizan205
ver 0.0.1 2019.10.05 ver 0.0.1 2019.10.05
''' '''
def _gen_vid(video_id): def _gen_vid(video_id):
"""generate video_id parameter. """generate video_id parameter.
Parameter Parameter
@@ -40,9 +41,11 @@ def _gen_vid(video_id):
b64enc(reduce(lambda x, y: x+y, item)).decode() b64enc(reduce(lambda x, y: x+y, item)).decode()
).encode() ).encode()
def _nval(val): def _nval(val):
"""convert value to byte array""" """convert value to byte array"""
if val<0: raise ValueError if val < 0:
raise ValueError
buf = b'' buf = b''
while val >> 7: while val >> 7:
m = val & 0xFF | 0x80 m = val & 0xFF | 0x80
@@ -51,6 +54,7 @@ def _nval(val):
buf += val.to_bytes(1, 'big') buf += val.to_bytes(1, 'big')
return buf return buf
def _build(video_id, seektime, topchat_only): def _build(video_id, seektime, topchat_only):
switch_01 = b'\x04' if topchat_only else b'\x01' switch_01 = b'\x04' if topchat_only else b'\x01'
if seektime < 0: if seektime < 0:
@@ -75,7 +79,8 @@ def _build(video_id, seektime, topchat_only):
sep_3 = b'\x00\x58\x03\x60' sep_3 = b'\x00\x58\x03\x60'
sep_4 = b'\x68' + parity + b'\x72\x04\x08' sep_4 = b'\x68' + parity + b'\x72\x04\x08'
sep_5 = b'\x10' + parity + b'\x78\x00' sep_5 = b'\x10' + parity + b'\x78\x00'
body = [
body = b''.join([
sep_0, sep_0,
_nval(len(vid)), _nval(len(vid)),
vid, vid,
@@ -90,9 +95,7 @@ def _build(video_id, seektime, topchat_only):
sep_4, sep_4,
switch_01, switch_01,
sep_5 sep_5
] ])
body = reduce(lambda x, y: x+y, body)
return urllib.parse.quote( return urllib.parse.quote(
b64enc(header_magic + b64enc(header_magic +
@@ -101,6 +104,7 @@ def _build(video_id, seektime, topchat_only):
).decode() ).decode()
) )
def getparam(video_id, seektime=0, topchat_only=False): def getparam(video_id, seektime=0, topchat_only=False):
''' '''
Parameter Parameter

View File

@@ -11,6 +11,8 @@ Author: taizan-hokuto (2019) @taizan205
ver 0.0.1 2019.10.05 ver 0.0.1 2019.10.05
''' '''
def _gen_vid(video_id): def _gen_vid(video_id):
"""generate video_id parameter. """generate video_id parameter.
Parameter Parameter
@@ -44,6 +46,7 @@ def _gen_vid(video_id):
b64enc(reduce(lambda x, y: x+y, item)).decode() b64enc(reduce(lambda x, y: x+y, item)).decode()
).encode() ).encode()
def _tzparity(video_id, times): def _tzparity(video_id, times):
t = 0 t = 0
for i, s in enumerate(video_id): for i, s in enumerate(video_id):
@@ -55,9 +58,11 @@ def _tzparity(video_id,times):
return ((times ^ t) % 2).to_bytes(1, 'big') return ((times ^ t) % 2).to_bytes(1, 'big')
def _nval(val): def _nval(val):
"""convert value to byte array""" """convert value to byte array"""
if val<0: raise ValueError if val < 0:
raise ValueError
buf = b'' buf = b''
while val >> 7: while val >> 7:
m = val & 0xFF | 0x80 m = val & 0xFF | 0x80
@@ -66,6 +71,7 @@ def _nval(val):
buf += val.to_bytes(1, 'big') buf += val.to_bytes(1, 'big')
return buf return buf
def _build(video_id, _ts1, _ts2, _ts3, _ts4, _ts5, topchat_only): def _build(video_id, _ts1, _ts2, _ts3, _ts4, _ts5, topchat_only):
# _short_type2 # _short_type2
switch_01 = b'\x04' if topchat_only else b'\x01' switch_01 = b'\x04' if topchat_only else b'\x01'
@@ -99,7 +105,7 @@ def _build(video_id, _ts1, _ts2, _ts3, _ts4, _ts5, topchat_only):
sep_9 = b'\x88\x01\x00\xA0\x01' sep_9 = b'\x88\x01\x00\xA0\x01'
timestamp5 = _nval(_ts5) timestamp5 = _nval(_ts5)
body = [ body = b''.join([
sep_0, sep_0,
_nval(len(vid)), _nval(len(vid)),
vid, vid,
@@ -121,15 +127,13 @@ def _build(video_id, _ts1, _ts2, _ts3, _ts4, _ts5, topchat_only):
ts_3_end, ts_3_end,
timestamp4, timestamp4,
sep_6, sep_6,
switch_01,# switch_01,
sep_7, sep_7,
switch_01,# switch_01,
sep_8, sep_8,
sep_9, sep_9,
timestamp5 timestamp5
] ])
body = reduce(lambda x, y: x+y, body)
return urllib.parse.quote( return urllib.parse.quote(
b64enc(header_magic + b64enc(header_magic +
@@ -161,4 +165,3 @@ def getparam(video_id, past_sec = 0, topchat_only = False):
if True, fetch only 'top chat' if True, fetch only 'top chat'
''' '''
return _build(video_id, *_times(past_sec), topchat_only) return _build(video_id, *_times(past_sec), topchat_only)

View File

@@ -4,10 +4,12 @@ from .renderer.textmessage import LiveChatTextMessageRenderer
from .renderer.paidmessage import LiveChatPaidMessageRenderer from .renderer.paidmessage import LiveChatPaidMessageRenderer
from .renderer.paidsticker import LiveChatPaidStickerRenderer from .renderer.paidsticker import LiveChatPaidStickerRenderer
from .renderer.legacypaid import LiveChatLegacyPaidMessageRenderer from .renderer.legacypaid import LiveChatLegacyPaidMessageRenderer
from .renderer.membership import LiveChatMembershipItemRenderer
from .. chat_processor import ChatProcessor from .. chat_processor import ChatProcessor
from ... import config from ... import config
logger = config.logger(__name__) logger = config.logger(__name__)
class CompatibleProcessor(ChatProcessor): class CompatibleProcessor(ChatProcessor):
def process(self, chat_components: list): def process(self, chat_components: list):
@@ -24,11 +26,15 @@ class CompatibleProcessor(ChatProcessor):
timeout += chat_component.get('timeout', 0) timeout += chat_component.get('timeout', 0)
chatdata = chat_component.get('chatdata') chatdata = chat_component.get('chatdata')
if chatdata is None: break if chatdata is None:
break
for action in chatdata: for action in chatdata:
if action is None: continue if action is None:
if action.get('addChatItemAction') is None: continue continue
if action['addChatItemAction'].get('item') is None: continue 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: if chat:
@@ -47,7 +53,8 @@ class CompatibleProcessor(ChatProcessor):
action = sitem.get("addChatItemAction") action = sitem.get("addChatItemAction")
if action: if action:
item = action.get("item") item = action.get("item")
if item is None: return None if item is None:
return None
rd = {} rd = {}
try: try:
renderer = self.get_renderer(item) renderer = self.get_renderer(item)
@@ -75,7 +82,8 @@ class CompatibleProcessor(ChatProcessor):
renderer = LiveChatPaidStickerRenderer(item) renderer = LiveChatPaidStickerRenderer(item)
elif item.get("liveChatLegacyPaidMessageRenderer"): elif item.get("liveChatLegacyPaidMessageRenderer"):
renderer = LiveChatLegacyPaidMessageRenderer(item) renderer = LiveChatLegacyPaidMessageRenderer(item)
elif item.get("liveChatMembershipItemRenderer"):
renderer = LiveChatMembershipItemRenderer(item)
else: else:
renderer = None renderer = None
return renderer return renderer

View File

@@ -0,0 +1,40 @@
from .base import BaseRenderer
class LiveChatMembershipItemRenderer(BaseRenderer):
def __init__(self, item):
super().__init__(item, "newSponsorEvent")
def get_snippet(self):
message = self.get_message(self.renderer)
return {
"type": self.chattype,
"liveChatId": "",
"authorChannelId": self.renderer.get("authorExternalChannelId"),
"publishedAt": self.get_publishedat(self.renderer.get("timestampUsec", 0)),
"hasDisplayContent": True,
"displayMessage": message,
}
def get_authordetails(self):
authorExternalChannelId = self.renderer.get("authorExternalChannelId")
# parse subscriber type
isVerified, isChatOwner, _, isChatModerator = (
self.get_badges(self.renderer)
)
return {
"channelId": authorExternalChannelId,
"channelUrl": "http://www.youtube.com/channel/"+authorExternalChannelId,
"displayName": self.renderer["authorName"]["simpleText"],
"profileImageUrl": self.renderer["authorPhoto"]["thumbnails"][1]["url"],
"isVerified": isVerified,
"isChatOwner": isChatOwner,
"isChatSponsor": True,
"isChatModerator": isChatModerator
}
def get_message(self, renderer):
message = ''.join([mes.get("text", "") for mes in renderer["headerSubtext"]["runs"]])
return message, [message]

View File

@@ -4,10 +4,13 @@ from .renderer.textmessage import LiveChatTextMessageRenderer
from .renderer.paidmessage import LiveChatPaidMessageRenderer from .renderer.paidmessage import LiveChatPaidMessageRenderer
from .renderer.paidsticker import LiveChatPaidStickerRenderer from .renderer.paidsticker import LiveChatPaidStickerRenderer
from .renderer.legacypaid import LiveChatLegacyPaidMessageRenderer from .renderer.legacypaid import LiveChatLegacyPaidMessageRenderer
from .renderer.membership import LiveChatMembershipItemRenderer
from .. chat_processor import ChatProcessor from .. chat_processor import ChatProcessor
from ... import config from ... import config
logger = config.logger(__name__) logger = config.logger(__name__)
class Chatdata: class Chatdata:
def __init__(self, chatlist: list, timeout: float): def __init__(self, chatlist: list, timeout: float):
self.items = chatlist self.items = chatlist
@@ -25,6 +28,7 @@ class Chatdata:
return return
await asyncio.sleep(self.interval/len(self.items)) await asyncio.sleep(self.interval/len(self.items))
class DefaultProcessor(ChatProcessor): class DefaultProcessor(ChatProcessor):
def process(self, chat_components: list): def process(self, chat_components: list):
@@ -35,24 +39,27 @@ class DefaultProcessor(ChatProcessor):
for component in chat_components: for component in chat_components:
timeout += component.get('timeout', 0) timeout += component.get('timeout', 0)
chatdata = component.get('chatdata') chatdata = component.get('chatdata')
if chatdata is None: continue if chatdata is None:
continue
for action in chatdata: for action in chatdata:
if action is None: continue if action is None:
if action.get('addChatItemAction') is None: continue continue
if action['addChatItemAction'].get('item') is None: continue 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: if chat:
chatlist.append(chat) chatlist.append(chat)
return Chatdata(chatlist, float(timeout)) return Chatdata(chatlist, float(timeout))
def _parse(self, sitem): def _parse(self, sitem):
action = sitem.get("addChatItemAction") action = sitem.get("addChatItemAction")
if action: if action:
item = action.get("item") item = action.get("item")
if item is None: return None if item is None:
return None
try: try:
renderer = self._get_renderer(item) renderer = self._get_renderer(item)
if renderer == None: if renderer == None:
@@ -74,6 +81,8 @@ class DefaultProcessor(ChatProcessor):
renderer = LiveChatPaidStickerRenderer(item) renderer = LiveChatPaidStickerRenderer(item)
elif item.get("liveChatLegacyPaidMessageRenderer"): elif item.get("liveChatLegacyPaidMessageRenderer"):
renderer = LiveChatLegacyPaidMessageRenderer(item) renderer = LiveChatLegacyPaidMessageRenderer(item)
elif item.get("liveChatMembershipItemRenderer"):
renderer = LiveChatMembershipItemRenderer(item)
else: else:
renderer = None renderer = None
return renderer return renderer

View File

@@ -0,0 +1,15 @@
from .base import BaseRenderer
class LiveChatMembershipItemRenderer(BaseRenderer):
def __init__(self, item):
super().__init__(item, "newSponsor")
def get_authordetails(self):
super().get_authordetails()
self.author.isChatSponsor = True
def get_message(self, renderer):
message = ''.join([mes.get("text", "") for mes in renderer["headerSubtext"]["runs"]])
return message, [message]

View File

@@ -8,6 +8,11 @@ PATTERN = re.compile(r"(.*)\(([0-9]+)\)$")
fmt_headers = ['datetime','elapsed','authorName','message','superchat' fmt_headers = ['datetime','elapsed','authorName','message','superchat'
,'type','authorChannel'] ,'type','authorChannel']
HEADER_HTML = '''
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
<meta http-equiv="Content-Type" content="text/html;charset=UTF-8">
'''
class HTMLArchiver(ChatProcessor): class HTMLArchiver(ChatProcessor):
''' '''
HtmlArchiver saves chat data as HTML table format. HtmlArchiver saves chat data as HTML table format.
@@ -17,6 +22,7 @@ class HTMLArchiver(ChatProcessor):
super().__init__() super().__init__()
self.save_path = self._checkpath(save_path) self.save_path = self._checkpath(save_path)
with open(self.save_path, mode='a', encoding = 'utf-8') as f: with open(self.save_path, mode='a', encoding = 'utf-8') as f:
f.write(HEADER_HTML)
f.write('<table border="1" style="border-collapse: collapse">') f.write('<table border="1" style="border-collapse: collapse">')
f.writelines(self._parse_html_header(fmt_headers)) f.writelines(self._parse_html_header(fmt_headers))
self.processor = DefaultProcessor() self.processor = DefaultProcessor()

View File

@@ -7,12 +7,15 @@ from . worker import ExtractWorker
from . patch import Patch from . patch import Patch
from ... import config from ... import config
from ... paramgen import arcparam from ... paramgen import arcparam
from ... exceptions import UnknownConnectionError
from concurrent.futures import CancelledError from concurrent.futures import CancelledError
from json import JSONDecodeError
from urllib.parse import quote from urllib.parse import quote
headers = config.headers headers = config.headers
REPLAY_URL = "https://www.youtube.com/live_chat_replay/" \ REPLAY_URL = "https://www.youtube.com/live_chat_replay/" \
"get_live_chat_replay?continuation=" "get_live_chat_replay?continuation="
MAX_RETRY_COUNT = 3
def _split(start, end, count, min_interval_sec = 120): def _split(start, end, count, min_interval_sec = 120):
""" """
@@ -57,9 +60,18 @@ def ready_blocks(video_id, duration, div, callback):
async def _create_block(session, video_id, seektime, callback): async def _create_block(session, video_id, seektime, callback):
continuation = arcparam.getparam(video_id, seektime = seektime) continuation = arcparam.getparam(video_id, seektime = seektime)
url = f"{REPLAY_URL}{quote(continuation)}&pbj=1" url = f"{REPLAY_URL}{quote(continuation)}&pbj=1"
for _ in range(MAX_RETRY_COUNT):
try :
async with session.get(url, headers = headers) as resp: async with session.get(url, headers = headers) as resp:
text = await resp.text() text = await resp.text()
next_continuation, actions = parser.parse(json.loads(text)) next_continuation, actions = parser.parse(json.loads(text))
break
except JSONDecodeError:
await asyncio.sleep(3)
else:
cancel()
raise UnknownConnectionError("Abort: Unknown connection error.")
if actions: if actions:
first = parser.get_offset(actions[0]) first = parser.get_offset(actions[0])
last = parser.get_offset(actions[-1]) last = parser.get_offset(actions[-1])
@@ -71,6 +83,7 @@ def ready_blocks(video_id, duration, div, callback):
first = first, first = first,
last = last last = last
) )
""" """
fetch initial blocks. fetch initial blocks.
""" """
@@ -95,9 +108,18 @@ def fetch_patch(callback, blocks, video_id):
async def _fetch(continuation,session) -> Patch: async def _fetch(continuation,session) -> Patch:
url = f"{REPLAY_URL}{quote(continuation)}&pbj=1" url = f"{REPLAY_URL}{quote(continuation)}&pbj=1"
for _ in range(MAX_RETRY_COUNT):
try:
async with session.get(url,headers = config.headers) as resp: async with session.get(url,headers = config.headers) as resp:
chat_json = await resp.text() chat_json = await resp.text()
continuation, actions = parser.parse(json.loads(chat_json)) continuation, actions = parser.parse(json.loads(chat_json))
break
except JSONDecodeError:
await asyncio.sleep(3)
else:
cancel()
raise UnknownConnectionError("Abort: Unknown connection error.")
if actions: if actions:
last = parser.get_offset(actions[-1]) last = parser.get_offset(actions[-1])
first = parser.get_offset(actions[0]) first = parser.get_offset(actions[0])
@@ -105,6 +127,7 @@ def fetch_patch(callback, blocks, video_id):
callback(actions, last - first) callback(actions, last - first)
return Patch(actions, continuation, first, last) return Patch(actions, continuation, first, last)
return Patch(continuation = continuation) return Patch(continuation = continuation)
""" """
allocate workers and assign blocks. allocate workers and assign blocks.
""" """

View File

@@ -70,7 +70,8 @@ def check_duplicate_offset(chatdata):
if is_duplicate(i,i+1)] if is_duplicate(i,i+1)]
def remove_duplicate_head(blocks): def remove_duplicate_head(blocks):
if len(blocks) == 1 : return blocks if len(blocks) == 0 or len(blocks) == 1:
return blocks
def is_duplicate_head(index): def is_duplicate_head(index):
@@ -97,7 +98,8 @@ def remove_duplicate_head(blocks):
return ret return ret
def remove_duplicate_tail(blocks): def remove_duplicate_tail(blocks):
if len(blocks) == 1 : return blocks if len(blocks) == 0 or len(blocks) == 1:
return blocks
def is_duplicate_tail(index): def is_duplicate_tail(index):
if len(blocks[index].chat_data) == 0: if len(blocks[index].chat_data) == 0:
@@ -126,7 +128,8 @@ def remove_overlap(blocks):
Align the last offset of each block to the first offset Align the last offset of each block to the first offset
of next block (equals `end` offset of each block). of next block (equals `end` offset of each block).
""" """
if len(blocks) == 1 : return blocks if len(blocks) == 0 or len(blocks) == 1:
return blocks
for block in blocks: for block in blocks:
if block.is_last: if block.is_last:

View File

@@ -40,6 +40,7 @@ class Extractor:
return self return self
def _set_block_end(self): def _set_block_end(self):
if len(self.blocks) > 0:
for i in range(len(self.blocks)-1): for i in range(len(self.blocks)-1):
self.blocks[i].end = self.blocks[i+1].first self.blocks[i].end = self.blocks[i+1].first
self.blocks[-1].end = self.duration*1000 self.blocks[-1].end = self.duration*1000

View File

@@ -36,7 +36,7 @@ def test_process_0():
chat_component = { chat_component = {
'video_id':'', 'video_id':'',
'timeout':10, 'timeout':10,
'chatdata':load_chatdata(r"tests\testdata\calculator\superchat_0.json") 'chatdata':load_chatdata(r"tests/testdata/calculator/superchat_0.json")
} }
assert SuperchatCalculator().process([chat_component])=={'': 6800.0, '': 2.0} assert SuperchatCalculator().process([chat_component])=={'': 6800.0, '': 2.0}
@@ -47,7 +47,7 @@ def test_process_1():
chat_component = { chat_component = {
'video_id':'', 'video_id':'',
'timeout':10, 'timeout':10,
'chatdata':load_chatdata(r"tests\testdata\calculator\text_only.json") 'chatdata':load_chatdata(r"tests/testdata/calculator/text_only.json")
} }
assert SuperchatCalculator().process([chat_component])=={} assert SuperchatCalculator().process([chat_component])=={}
@@ -59,7 +59,7 @@ def test_process_2():
chat_component = { chat_component = {
'video_id':'', 'video_id':'',
'timeout':10, 'timeout':10,
'chatdata':load_chatdata(r"tests\testdata\calculator\replay_end.json") 'chatdata':load_chatdata(r"tests/testdata/calculator/replay_end.json")
} }
assert False assert False
SuperchatCalculator().process([chat_component]) SuperchatCalculator().process([chat_component])

View File

@@ -1,6 +1,7 @@
import json import json
import pytest import pytest
import asyncio,aiohttp import asyncio
import aiohttp
from pytchat.parser.live import Parser from pytchat.parser.live import Parser
from pytchat.processors.compatible.processor import CompatibleProcessor from pytchat.processors.compatible.processor import CompatibleProcessor
from pytchat.exceptions import ( from pytchat.exceptions import (
@@ -14,6 +15,7 @@ from pytchat.processors.compatible.renderer.legacypaid import LiveChatLegacyPaid
parser = Parser(is_replay=False) parser = Parser(is_replay=False)
def test_textmessage(mocker): def test_textmessage(mocker):
'''api互換processorのテスト通常テキストメッセージ''' '''api互換processorのテスト通常テキストメッセージ'''
processor = CompatibleProcessor() processor = CompatibleProcessor()
@@ -51,6 +53,7 @@ def test_textmessage(mocker):
assert "LCC." in ret["items"][0]["id"] assert "LCC." in ret["items"][0]["id"]
assert ret["items"][0]["snippet"]["type"] == "textMessageEvent" assert ret["items"][0]["snippet"]["type"] == "textMessageEvent"
def test_newsponcer(mocker): def test_newsponcer(mocker):
'''api互換processorのテストメンバ新規登録''' '''api互換processorのテストメンバ新規登録'''
processor = CompatibleProcessor() processor = CompatibleProcessor()
@@ -87,6 +90,42 @@ def test_newsponcer(mocker):
assert ret["items"][0]["snippet"]["type"] == "newSponsorEvent" assert ret["items"][0]["snippet"]["type"] == "newSponsorEvent"
def test_newsponcer_rev(mocker):
'''api互換processorのテストメンバ新規登録'''
processor = CompatibleProcessor()
_json = _open_file("tests/testdata/compatible/newSponsor_rev.json")
_, chatdata = parser.parse(parser.get_contents(json.loads(_json)))
data = {
"video_id": "",
"timeout": 7,
"chatdata": chatdata
}
ret = processor.process([data])
assert ret["kind"] == "youtube#liveChatMessageListResponse"
assert ret["pollingIntervalMillis"] == data["timeout"]*1000
assert ret.keys() == {
"kind", "etag", "pageInfo", "nextPageToken", "pollingIntervalMillis", "items"
}
assert ret["pageInfo"].keys() == {
"totalResults", "resultsPerPage"
}
assert ret["items"][0].keys() == {
"kind", "etag", "id", "snippet", "authorDetails"
}
assert ret["items"][0]["snippet"].keys() == {
'type', 'liveChatId', 'authorChannelId', 'publishedAt', 'hasDisplayContent', 'displayMessage'
}
assert ret["items"][0]["authorDetails"].keys() == {
'channelId', 'channelUrl', 'displayName', 'profileImageUrl', 'isVerified', 'isChatOwner', 'isChatSponsor', 'isChatModerator'
}
assert "LCC." in ret["items"][0]["id"]
assert ret["items"][0]["snippet"]["type"] == "newSponsorEvent"
def test_superchat(mocker): def test_superchat(mocker):
'''api互換processorのテストスパチャ''' '''api互換processorのテストスパチャ'''
processor = CompatibleProcessor() processor = CompatibleProcessor()
@@ -124,6 +163,7 @@ def test_superchat(mocker):
assert "LCC." in ret["items"][0]["id"] assert "LCC." in ret["items"][0]["id"]
assert ret["items"][0]["snippet"]["type"] == "superChatEvent" assert ret["items"][0]["snippet"]["type"] == "superChatEvent"
def test_unregistered_currency(mocker): def test_unregistered_currency(mocker):
processor = CompatibleProcessor() processor = CompatibleProcessor()

File diff suppressed because it is too large Load Diff