Compare commits

..

17 Commits

Author SHA1 Message Date
taizan-hokuto
cd6d522055 Merge branch 'release/v0.1.0' 2020-07-24 16:27:14 +09:00
taizan-hokuto
aa8a4fb592 Increment version 2020-07-24 16:26:09 +09:00
taizan-hokuto
dbde072828 Merge branch 'hotfix/fix_exception_handling' 2020-07-24 15:20:08 +09:00
taizan-hokuto
92a01aa4d9 Merge tag 'fix_exception_handling' into develop 2020-07-24 15:20:08 +09:00
taizan-hokuto
e3f9f95fb1 Fix exception handling 2020-07-24 15:19:32 +09:00
taizan-hokuto
fa02116ab4 Merge branch 'feature/url_pattern' into develop 2020-07-24 14:52:06 +09:00
taizan-hokuto
d8656161cd Update README 2020-07-24 14:04:13 +09:00
taizan-hokuto
174d9f27c0 Add tests 2020-07-24 14:03:20 +09:00
taizan-hokuto
0abf8dd9f0 Make it possible to extract video id from url 2020-07-24 14:03:07 +09:00
taizan-hokuto
5ab653a1b2 Merge branch 'feature/extend_processor' into develop 2020-07-23 16:35:37 +09:00
taizan-hokuto
6e6bb8e019 Add tests 2020-07-23 16:20:38 +09:00
taizan-hokuto
ee4b696fc5 Add colors attribute 2020-07-23 16:20:12 +09:00
taizan-hokuto
fd1d283caa Merge branch 'hotfix/meta_tag' 2020-07-13 23:04:19 +09:00
taizan-hokuto
85966186b5 Merge tag 'meta_tag' into develop
v0.0.9.1
2020-07-13 23:04:19 +09:00
taizan-hokuto
71341d2876 Increment version 2020-07-13 23:03:46 +09:00
taizan-hokuto
8882c82f8b Fix place of meta tag 2020-07-13 23:03:20 +09:00
taizan-hokuto
584b9c5591 Merge tag 'v0.0.9' into develop
v0.0.9
2020-07-13 01:55:13 +09:00
24 changed files with 1064 additions and 55 deletions

View File

@@ -7,7 +7,7 @@ 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.
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。
pytchatはYouTubeチャットを閲覧するためのpythonライブラリです。
Other features:
+ Customizable [chat data processors](https://github.com/taizan-hokuto/pytchat/wiki/ChatProcessor) including youtube api compatible one.
@@ -30,10 +30,9 @@ One-liner command.
Save chat data to html, with embedded custom emojis.
```bash
$ pytchat -v ZJ6Q4U_Vg6s -o "c:/temp/"
$ pytchat -v https://www.youtube.com/watch?v=ZJ6Q4U_Vg6s -o "c:/temp/"
# options:
# -v : video_id
# -v : Video ID or URL that includes ID
# -o : output directory (default path: './')
# saved filename is [video_id].html
```
@@ -43,7 +42,8 @@ $ pytchat -v ZJ6Q4U_Vg6s -o "c:/temp/"
```python
from pytchat import LiveChat
livechat = LiveChat(video_id = "Zvp1pJpie4I")
# It is also possible to specify a URL that includes the video ID:
# livechat = LiveChat("https://www.youtube.com/watch?v=Zvp1pJpie4I")
while livechat.is_alive():
try:
chatdata = livechat.get()

View File

@@ -2,7 +2,7 @@
pytchat is a lightweight python library to browse youtube livechat without Selenium or BeautifulSoup.
"""
__copyright__ = 'Copyright (C) 2019 taizan-hokuto'
__version__ = '0.0.9'
__version__ = '0.1.0'
__license__ = 'MIT'
__author__ = 'taizan-hokuto'
__author_email__ = '55448286+taizan-hokuto@users.noreply.github.com'

View File

@@ -1,5 +1,6 @@
import argparse
from pathlib import Path
from pytchat.util.extract_video_id import extract_video_id
from .arguments import Arguments
from .. exceptions import InvalidVideoIdException, NoContents
from .. processors.html_archiver import HTMLArchiver
@@ -19,16 +20,19 @@ https://github.com/PetterKraabol/Twitch-Chat-Downloader
def main():
# Arguments
parser = argparse.ArgumentParser(description=f'pytchat v{__version__}')
parser.add_argument('-v', f'--{Arguments.Name.VIDEO}', type=str,
help='Video IDs separated by commas without space.\n'
# parser.add_argument('VideoID_or_URL', type=str, default='__NONE__',nargs='?',
# help='Video ID, or URL that includes id.\n'
# 'If ID starts with a hyphen (-), enclose the ID in square brackets.')
parser.add_argument('-v', f'--{Arguments.Name.VIDEO_IDS}', type=str,
help='Video ID (or URL that includes Video ID). You can specify multiple video IDs by separating them with commas without spaces.\n'
'If ID starts with a hyphen (-), enclose the ID in square brackets.')
parser.add_argument('-o', f'--{Arguments.Name.OUTPUT}', type=str,
help='Output directory (end with "/"). default="./"', default='./')
parser.add_argument(f'--{Arguments.Name.VERSION}', action='store_true',
help='Settings version')
help='Show version')
Arguments(parser.parse_args().__dict__)
if Arguments().print_version:
print(f'pytchat v{__version__}')
print(f'pytchat v{__version__} © 2019 taizan-hokuto')
return
# Extractor
@@ -43,14 +47,16 @@ def main():
f" channel: {info.get_channel_name()}\n"
f" title: {info.get_title()}")
path = Path(Arguments().output + video_id + '.html')
print(f"output path: {path.resolve()}")
print(f" output path: {path.resolve()}")
Extractor(video_id,
processor=HTMLArchiver(
Arguments().output + video_id + '.html'),
callback=_disp_progress
).extract()
print("\nExtraction end.\n")
except (InvalidVideoIdException, NoContents) as e:
except InvalidVideoIdException:
print("Invalid Video ID or URL:", video_id)
except (TypeError, NoContents) as e:
print(e)
return
parser.print_help()

View File

@@ -16,8 +16,8 @@ class Arguments(metaclass=Singleton):
class Name:
VERSION: str = 'version'
OUTPUT: str = 'output'
VIDEO: str = 'video'
OUTPUT: str = 'output_dir'
VIDEO_IDS: str = 'video_id'
def __init__(self,
arguments: Optional[Dict[str, Union[str, bool, int]]] = None):
@@ -35,6 +35,9 @@ class Arguments(metaclass=Singleton):
self.output: str = arguments[Arguments.Name.OUTPUT]
self.video_ids: List[int] = []
# Videos
if arguments[Arguments.Name.VIDEO]:
if arguments[Arguments.Name.VIDEO_IDS]:
self.video_ids = [video_id
for video_id in arguments[Arguments.Name.VIDEO].split(',')]
for video_id in arguments[Arguments.Name.VIDEO_IDS].split(',')]

View File

@@ -15,6 +15,7 @@ from .. import exceptions
from ..paramgen import liveparam, arcparam
from ..processors.default.processor import DefaultProcessor
from ..processors.combinator import Combinator
from ..util.extract_video_id import extract_video_id
headers = config.headers
MAX_RETRY = 10
@@ -86,7 +87,7 @@ class LiveChatAsync:
topchat_only=False,
logger=config.logger(__name__),
):
self._video_id = video_id
self._video_id = extract_video_id(video_id)
self.seektime = seektime
if isinstance(processor, tuple):
self.processor = Combinator(processor)
@@ -333,12 +334,12 @@ class LiveChatAsync:
'''
if self.is_alive():
self.terminate()
try:
self.listen_task.result()
except Exception as e:
self.exception = e
if not isinstance(e, exceptions.ChatParseException):
self._logger.error(f'Internal exception - {type(e)}{str(e)}')
try:
self.listen_task.result()
except Exception as e:
self.exception = e
if not isinstance(e, exceptions.ChatParseException):
self._logger.error(f'Internal exception - {type(e)}{str(e)}')
self._logger.info(f'[{self._video_id}]終了しました')
def raise_for_status(self):

View File

@@ -14,6 +14,7 @@ from .. import exceptions
from ..paramgen import liveparam, arcparam
from ..processors.default.processor import DefaultProcessor
from ..processors.combinator import Combinator
from ..util.extract_video_id import extract_video_id
headers = config.headers
MAX_RETRY = 10
@@ -84,7 +85,7 @@ class LiveChat:
topchat_only=False,
logger=config.logger(__name__)
):
self._video_id = video_id
self._video_id = extract_video_id(video_id)
self.seektime = seektime
if isinstance(processor, tuple):
self.processor = Combinator(processor)
@@ -324,12 +325,12 @@ class LiveChat:
'''
if self.is_alive():
self.terminate()
try:
self.listen_task.result()
except Exception as e:
self.exception = e
if not isinstance(e, exceptions.ChatParseException):
self._logger.error(f'Internal exception - {type(e)}{str(e)}')
try:
self.listen_task.result()
except Exception as e:
self.exception = e
if not isinstance(e, exceptions.ChatParseException):
self._logger.error(f'Internal exception - {type(e)}{str(e)}')
self._logger.info(f'[{self._video_id}]終了しました')
def raise_for_status(self):

View File

@@ -12,4 +12,4 @@ class LiveChatLegacyPaidMessageRenderer(BaseRenderer):
def get_message(self, renderer):
message = (renderer["eventText"]["runs"][0]["text"]
) + ' / ' + (renderer["detailText"]["simpleText"])
return message
return message, [message]

View File

@@ -4,6 +4,10 @@ from .base import BaseRenderer
superchat_regex = re.compile(r"^(\D*)(\d{1,3}(,\d{3})*(\.\d*)*\b)$")
class Colors:
pass
class LiveChatPaidMessageRenderer(BaseRenderer):
def __init__(self, item):
super().__init__(item, "superChat")
@@ -18,6 +22,7 @@ class LiveChatPaidMessageRenderer(BaseRenderer):
self.currency = currency.symbols[symbol]["fxtext"] if currency.symbols.get(
symbol) else symbol
self.bgColor = self.renderer.get("bodyBackgroundColor", 0)
self.colors = self.get_colors()
def get_amountdata(self, renderer):
amountDisplayString = renderer["purchaseAmountText"]["simpleText"]
@@ -29,3 +34,13 @@ class LiveChatPaidMessageRenderer(BaseRenderer):
symbol = ""
amount = 0.0
return amountDisplayString, symbol, amount
def get_colors(self):
colors = Colors()
colors.headerBackgroundColor = self.renderer.get("headerBackgroundColor", 0)
colors.headerTextColor = self.renderer.get("headerTextColor", 0)
colors.bodyBackgroundColor = self.renderer.get("bodyBackgroundColor", 0)
colors.bodyTextColor = self.renderer.get("bodyTextColor", 0)
colors.timestampColor = self.renderer.get("timestampColor", 0)
colors.authorNameTextColor = self.renderer.get("authorNameTextColor", 0)
return colors

View File

@@ -4,6 +4,10 @@ from .base import BaseRenderer
superchat_regex = re.compile(r"^(\D*)(\d{1,3}(,\d{3})*(\.\d*)*\b)$")
class Colors:
pass
class LiveChatPaidStickerRenderer(BaseRenderer):
def __init__(self, item):
super().__init__(item, "superSticker")
@@ -18,8 +22,9 @@ class LiveChatPaidStickerRenderer(BaseRenderer):
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"]
self.sticker = "".join(("https:",
self.renderer["sticker"]["thumbnails"][0]["url"]))
self.colors = self.get_colors()
def get_amountdata(self, renderer):
amountDisplayString = renderer["purchaseAmountText"]["simpleText"]
@@ -31,3 +36,11 @@ class LiveChatPaidStickerRenderer(BaseRenderer):
symbol = ""
amount = 0.0
return amountDisplayString, symbol, amount
def get_colors(self):
colors = Colors()
colors.moneyChipBackgroundColor = self.renderer.get("moneyChipBackgroundColor", 0)
colors.moneyChipTextColor = self.renderer.get("moneyChipTextColor", 0)
colors.backgroundColor = self.renderer.get("backgroundColor", 0)
colors.authorNameTextColor = self.renderer.get("authorNameTextColor", 0)
return colors

View File

@@ -12,9 +12,9 @@ fmt_headers = ['datetime', 'elapsed', 'authorName',
'message', 'superchat', 'type', 'authorChannel']
HEADER_HTML = '''
<meta http-equiv="Content-Type" content="text/html;charset=UTF-8">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html;charset=UTF-8">
'''
TABLE_CSS = '''
@@ -47,7 +47,7 @@ class HTMLArchiver(ChatProcessor):
super().__init__()
self.save_path = self._checkpath(save_path)
self.processor = DefaultProcessor()
self.emoji_table = {} # table for custom emojis. key: emoji_id, value: base64 encoded image binary.
self.emoji_table = {} # tuble for custom emojis. key: emoji_id, value: base64 encoded image binary.
self.header = [HEADER_HTML]
self.body = ['<body>\n', '<table class="css">\n', self._parse_table_header(fmt_headers)]

View File

@@ -3,6 +3,7 @@ from . import duplcheck
from .. videoinfo import VideoInfo
from ... import config
from ... exceptions import InvalidVideoIdException
from ... util.extract_video_id import extract_video_id
logger = config.logger(__name__)
headers = config.headers
@@ -14,7 +15,7 @@ class Extractor:
raise ValueError('div must be positive integer.')
elif div > 10:
div = 10
self.video_id = video_id
self.video_id = extract_video_id(video_id)
self.div = div
self.callback = callback
self.processor = processor

View File

@@ -3,6 +3,7 @@ import re
import requests
from .. import config
from ..exceptions import InvalidVideoIdException
from ..util.extract_video_id import extract_video_id
headers = config.headers
@@ -78,8 +79,8 @@ class VideoInfo:
'''
def __init__(self, video_id):
self.video_id = video_id
text = self._get_page_text(video_id)
self.video_id = extract_video_id(video_id)
text = self._get_page_text(self.video_id)
self._parse(text)
def _get_page_text(self, video_id):

View File

@@ -0,0 +1,25 @@
import re
from .. exceptions import InvalidVideoIdException
PATTERN = re.compile(r"((?<=(v|V)/)|(?<=be/)|(?<=(\?|\&)v=)|(?<=embed/))([\w-]+)")
YT_VIDEO_ID_LENGTH = 11
def extract_video_id(url_or_id: str) -> str:
ret = ''
if type(url_or_id) != str:
raise TypeError(f"{url_or_id}: URL or VideoID must be str, but {type(url_or_id)} is passed.")
if len(url_or_id) == YT_VIDEO_ID_LENGTH:
return url_or_id
match = re.search(PATTERN, url_or_id)
if match is None:
raise InvalidVideoIdException(url_or_id)
try:
ret = match.group(4)
except IndexError:
raise InvalidVideoIdException(url_or_id)
if ret is None or len(ret) != YT_VIDEO_ID_LENGTH:
raise InvalidVideoIdException(url_or_id)
return ret

View File

@@ -0,0 +1,228 @@
import json
from pytchat.parser.live import Parser
from pytchat.processors.default.processor import DefaultProcessor
def test_textmessage(mocker):
'''text message'''
processor = DefaultProcessor()
parser = Parser(is_replay=False)
_json = _open_file("tests/testdata/default/textmessage.json")
_, chatdata = parser.parse(parser.get_contents(json.loads(_json)))
data = {
"video_id": "",
"timeout": 7,
"chatdata": chatdata
}
ret = processor.process([data]).items[0]
assert ret.chattype == "textMessage"
assert ret.id == "dummy_id"
assert ret.message == "dummy_message"
assert ret.timestamp == 1570678496000
assert ret.datetime == "2019-10-10 12:34:56"
assert ret.author.name == "author_name"
assert ret.author.channelId == "author_channel_id"
assert ret.author.channelUrl == "http://www.youtube.com/channel/author_channel_id"
assert ret.author.imageUrl == "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg"
assert ret.author.badgeUrl == ""
assert ret.author.isVerified is False
assert ret.author.isChatOwner is False
assert ret.author.isChatSponsor is False
assert ret.author.isChatModerator is False
def test_textmessage_replay_member(mocker):
'''text message replay member'''
processor = DefaultProcessor()
parser = Parser(is_replay=True)
_json = _open_file("tests/testdata/default/replay_member_text.json")
_, chatdata = parser.parse(parser.get_contents(json.loads(_json)))
data = {
"video_id": "",
"timeout": 7,
"chatdata": chatdata
}
ret = processor.process([data]).items[0]
assert ret.chattype == "textMessage"
assert ret.type == "textMessage"
assert ret.id == "dummy_id"
assert ret.message == "dummy_message"
assert ret.messageEx == ["dummy_message"]
assert ret.timestamp == 1570678496000
assert ret.datetime == "2019-10-10 12:34:56"
assert ret.elapsedTime == "1:23:45"
assert ret.author.name == "author_name"
assert ret.author.channelId == "author_channel_id"
assert ret.author.channelUrl == "http://www.youtube.com/channel/author_channel_id"
assert ret.author.imageUrl == "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg"
assert ret.author.badgeUrl == "https://yt3.ggpht.com/X=s16-c-k"
assert ret.author.isVerified is False
assert ret.author.isChatOwner is False
assert ret.author.isChatSponsor is True
assert ret.author.isChatModerator is False
def test_superchat(mocker):
'''superchat'''
processor = DefaultProcessor()
parser = Parser(is_replay=False)
_json = _open_file("tests/testdata/default/superchat.json")
_, chatdata = parser.parse(parser.get_contents(json.loads(_json)))
data = {
"video_id": "",
"timeout": 7,
"chatdata": chatdata
}
ret = processor.process([data]).items[0]
print(json.dumps(chatdata, ensure_ascii=False))
assert ret.chattype == "superChat"
assert ret.type == "superChat"
assert ret.id == "dummy_id"
assert ret.message == "dummy_message"
assert ret.messageEx == ["dummy_message"]
assert ret.timestamp == 1570678496000
assert ret.datetime == "2019-10-10 12:34:56"
assert ret.elapsedTime == ""
assert ret.amountValue == 800
assert ret.amountString == "¥800"
assert ret.currency == "JPY"
assert ret.bgColor == 4280150454
assert ret.author.name == "author_name"
assert ret.author.channelId == "author_channel_id"
assert ret.author.channelUrl == "http://www.youtube.com/channel/author_channel_id"
assert ret.author.imageUrl == "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg"
assert ret.author.badgeUrl == ""
assert ret.author.isVerified is False
assert ret.author.isChatOwner is False
assert ret.author.isChatSponsor is False
assert ret.author.isChatModerator is False
assert ret.colors.headerBackgroundColor == 4278239141
assert ret.colors.headerTextColor == 4278190080
assert ret.colors.bodyBackgroundColor == 4280150454
assert ret.colors.bodyTextColor == 4278190080
assert ret.colors.authorNameTextColor == 2315255808
assert ret.colors.timestampColor == 2147483648
def test_supersticker(mocker):
'''supersticker'''
processor = DefaultProcessor()
parser = Parser(is_replay=False)
_json = _open_file("tests/testdata/default/supersticker.json")
_, chatdata = parser.parse(parser.get_contents(json.loads(_json)))
data = {
"video_id": "",
"timeout": 7,
"chatdata": chatdata
}
ret = processor.process([data]).items[0]
print(json.dumps(chatdata, ensure_ascii=False))
assert ret.chattype == "superSticker"
assert ret.type == "superSticker"
assert ret.id == "dummy_id"
assert ret.message == ""
assert ret.messageEx == []
assert ret.timestamp == 1570678496000
assert ret.datetime == "2019-10-10 12:34:56"
assert ret.elapsedTime == ""
assert ret.amountValue == 200
assert ret.amountString == "¥200"
assert ret.currency == "JPY"
assert ret.bgColor == 4278248959
assert ret.sticker == "https://lh3.googleusercontent.com/param_s=s72-rp"
assert ret.author.name == "author_name"
assert ret.author.channelId == "author_channel_id"
assert ret.author.channelUrl == "http://www.youtube.com/channel/author_channel_id"
assert ret.author.imageUrl == "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg"
assert ret.author.badgeUrl == ""
assert ret.author.isVerified is False
assert ret.author.isChatOwner is False
assert ret.author.isChatSponsor is False
assert ret.author.isChatModerator is False
assert ret.colors.backgroundColor == 4278237396
assert ret.colors.moneyChipBackgroundColor == 4278248959
assert ret.colors.moneyChipTextColor == 4278190080
assert ret.colors.authorNameTextColor == 3003121664
def test_sponsor(mocker):
'''sponsor(membership)'''
processor = DefaultProcessor()
parser = Parser(is_replay=False)
_json = _open_file("tests/testdata/default/newSponsor_current.json")
_, chatdata = parser.parse(parser.get_contents(json.loads(_json)))
data = {
"video_id": "",
"timeout": 7,
"chatdata": chatdata
}
ret = processor.process([data]).items[0]
print(json.dumps(chatdata, ensure_ascii=False))
assert ret.chattype == "newSponsor"
assert ret.type == "newSponsor"
assert ret.id == "dummy_id"
assert ret.message == "新規メンバー"
assert ret.messageEx == ["新規メンバー"]
assert ret.timestamp == 1570678496000
assert ret.datetime == "2019-10-10 12:34:56"
assert ret.elapsedTime == ""
assert ret.bgColor == 0
assert ret.author.name == "author_name"
assert ret.author.channelId == "author_channel_id"
assert ret.author.channelUrl == "http://www.youtube.com/channel/author_channel_id"
assert ret.author.imageUrl == "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg"
assert ret.author.badgeUrl == "https://yt3.ggpht.com/X=s32-c-k"
assert ret.author.isVerified is False
assert ret.author.isChatOwner is False
assert ret.author.isChatSponsor is True
assert ret.author.isChatModerator is False
def test_sponsor_legacy(mocker):
'''lagacy sponsor(membership)'''
processor = DefaultProcessor()
parser = Parser(is_replay=False)
_json = _open_file("tests/testdata/default/newSponsor_lagacy.json")
_, chatdata = parser.parse(parser.get_contents(json.loads(_json)))
data = {
"video_id": "",
"timeout": 7,
"chatdata": chatdata
}
ret = processor.process([data]).items[0]
print(json.dumps(chatdata, ensure_ascii=False))
assert ret.chattype == "newSponsor"
assert ret.type == "newSponsor"
assert ret.id == "dummy_id"
assert ret.message == "新規メンバー / ようこそ、author_name"
assert ret.messageEx == ["新規メンバー / ようこそ、author_name"]
assert ret.timestamp == 1570678496000
assert ret.datetime == "2019-10-10 12:34:56"
assert ret.elapsedTime == ""
assert ret.bgColor == 0
assert ret.author.name == "author_name"
assert ret.author.channelId == "author_channel_id"
assert ret.author.channelUrl == "http://www.youtube.com/channel/author_channel_id"
assert ret.author.imageUrl == "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg"
assert ret.author.badgeUrl == ""
assert ret.author.isVerified is False
assert ret.author.isChatOwner is False
assert ret.author.isChatSponsor is True
assert ret.author.isChatModerator is False
def _open_file(path):
with open(path, mode='r', encoding='utf-8') as f:
return f.read()

View File

@@ -0,0 +1,55 @@
from pytchat.util.extract_video_id import extract_video_id
from pytchat.exceptions import InvalidVideoIdException
VALID_TEST_PATTERNS = (
("ABC_EFG_IJK", "ABC_EFG_IJK"),
("vid_test_be", "vid_test_be"),
("https://www.youtube.com/watch?v=123_456_789", "123_456_789"),
("https://www.youtube.com/watch?v=123_456_789&t=123s", "123_456_789"),
("www.youtube.com/watch?v=123_456_789", "123_456_789"),
("watch?v=123_456_789", "123_456_789"),
("youtube.com/watch?v=123_456_789", "123_456_789"),
("http://youtu.be/ABC_EFG_IJK", "ABC_EFG_IJK"),
("youtu.be/ABC_EFG_IJK", "ABC_EFG_IJK"),
("https://www.youtube.com/watch?v=ABC_EFG_IJK&list=XYZ_ABC_12345&start_radio=1&t=1", "ABC_EFG_IJK"),
("https://www.youtube.com/embed/ABC_EFG_IJK", "ABC_EFG_IJK"),
("www.youtube.com/embed/ABC_EFG_IJK", "ABC_EFG_IJK"),
("youtube.com/embed/ABC_EFG_IJK", "ABC_EFG_IJK")
)
INVALID_TEST_PATTERNS = (
("", ""),
("0123456789", "0123456789"), # less than 11 letters id
("more_than_11_letter_string", "more_than_11_letter_string"),
("https://www.youtube.com/watch?v=more_than_11_letter_string", "more_than_11_letter_string"),
("https://www.youtube.com/channel/123_456_789", "123_456_789"),
)
TYPEERROR_TEST_PATTERNS = (
(100, 100), # not string
(["123_456_789"], "123_456_789"), # not string
)
def test_extract_valid_pattern():
for pattern in VALID_TEST_PATTERNS:
ret = extract_video_id(pattern[0])
assert ret == pattern[1]
def test_extract_invalid_pattern():
for pattern in INVALID_TEST_PATTERNS:
try:
extract_video_id(pattern[0])
assert False
except InvalidVideoIdException:
assert True
def test_extract_typeerror_pattern():
for pattern in TYPEERROR_TEST_PATTERNS:
try:
extract_video_id(pattern[0])
assert False
except TypeError:
assert True

View File

@@ -11,13 +11,13 @@ def _open_file(path):
@aioresponses()
def test_Async(*mock):
vid = ''
vid = '__test_id__'
_text = _open_file('tests/testdata/paramgen_firstread.json')
_text = json.loads(_text)
mock[0].get(
f"https://www.youtube.com/live_chat?v={vid}&is_popout=1", status=200, body=_text)
try:
chat = LiveChatAsync(video_id='')
chat = LiveChatAsync(video_id='__test_id__')
assert chat.is_alive()
chat.terminate()
assert not chat.is_alive()
@@ -33,7 +33,7 @@ def test_MultiThread(mocker):
responseMock.text = _text
mocker.patch('requests.Session.get').return_value = responseMock
try:
chat = LiveChatAsync(video_id='')
chat = LiveChatAsync(video_id='__test_id__')
assert chat.is_alive()
chat.terminate()
assert not chat.is_alive()

View File

@@ -20,7 +20,7 @@ def test_async_live_stream(*mock):
r'^https://www.youtube.com/live_chat/get_live_chat\?continuation=.*$')
_text = _open_file('tests/testdata/test_stream.json')
mock[0].get(pattern, status=200, body=_text)
chat = LiveChatAsync(video_id='', processor=DummyProcessor())
chat = LiveChatAsync(video_id='__test_id__', processor=DummyProcessor())
chats = await chat.get()
rawdata = chats[0]["chatdata"]
# assert fetching livachat data
@@ -60,7 +60,7 @@ def test_async_replay_stream(*mock):
mock[0].get(pattern_live, status=200, body=_text_live)
mock[0].get(pattern_replay, status=200, body=_text_replay)
chat = LiveChatAsync(video_id='', processor=DummyProcessor())
chat = LiveChatAsync(video_id='__test_id__', processor=DummyProcessor())
chats = await chat.get()
rawdata = chats[0]["chatdata"]
# assert fetching replaychat data
@@ -93,7 +93,7 @@ def test_async_force_replay(*mock):
mock[0].get(pattern_replay, status=200, body=_text_replay)
# force replay
chat = LiveChatAsync(
video_id='', processor=DummyProcessor(), force_replay=True)
video_id='__test_id__', processor=DummyProcessor(), force_replay=True)
chats = await chat.get()
rawdata = chats[0]["chatdata"]
# assert fetching replaychat data
@@ -119,7 +119,7 @@ def test_multithread_live_stream(mocker):
mocker.patch(
'requests.Session.get').return_value.__enter__.return_value = responseMock
chat = LiveChat(video_id='test_id', processor=DummyProcessor())
chat = LiveChat(video_id='__test_id__', processor=DummyProcessor())
chats = chat.get()
rawdata = chats[0]["chatdata"]
# assert fetching livachat data

View File

@@ -1,11 +1,12 @@
from pytchat.tool.videoinfo import VideoInfo
from pytchat.exceptions import InvalidVideoIdException
import pytest
def _open_file(path):
with open(path,mode ='r',encoding = 'utf-8') as f:
with open(path, mode='r', encoding='utf-8') as f:
return f.read()
def _set_test_data(filepath, mocker):
_text = _open_file(filepath)
response_mock = mocker.Mock()
@@ -13,23 +14,25 @@ def _set_test_data(filepath, mocker):
response_mock.text = _text
mocker.patch('requests.get').return_value = response_mock
def test_archived_page(mocker):
_set_test_data('tests/testdata/videoinfo/archived_page.txt', mocker)
info = VideoInfo('test_id')
info = VideoInfo('__test_id__')
actual_thumbnail_url = 'https://i.ytimg.com/vi/fzI9FNjXQ0o/hqdefault.jpg'
assert info.video_id == 'test_id'
assert info.video_id == '__test_id__'
assert info.get_channel_name() == 'GitHub'
assert info.get_thumbnail() == actual_thumbnail_url
assert info.get_title() == 'GitHub Arctic Code Vault'
assert info.get_channel_id() == 'UC7c3Kb6jYCRj4JOHHZTxKsQ'
assert info.get_duration() == 148
def test_live_page(mocker):
_set_test_data('tests/testdata/videoinfo/live_page.txt', mocker)
info = VideoInfo('test_id')
info = VideoInfo('__test_id__')
'''live page :duration = 0'''
assert info.get_duration() == 0
assert info.video_id == 'test_id'
assert info.video_id == '__test_id__'
assert info.get_channel_name() == 'BGM channel'
assert info.get_thumbnail() == \
'https://i.ytimg.com/vi/fEvM-OUbaKs/hqdefault_live.jpg'
@@ -38,25 +41,26 @@ def test_live_page(mocker):
' - 24/7 Live Stream - Slow Jazz')
assert info.get_channel_id() == 'UCQINXHZqCU5i06HzxRkujfg'
def test_invalid_video_id(mocker):
'''Test case invalid video_id is specified.'''
_set_test_data(
'tests/testdata/videoinfo/invalid_video_id_page.txt', mocker)
try:
_ = VideoInfo('test_id')
_ = VideoInfo('__test_id__')
assert False
except InvalidVideoIdException:
assert True
def test_no_info(mocker):
'''Test case the video page has renderer, but no info.'''
_set_test_data(
'tests/testdata/videoinfo/no_info_page.txt', mocker)
info = VideoInfo('test_id')
assert info.video_id == 'test_id'
info = VideoInfo('__test_id__')
assert info.video_id == '__test_id__'
assert info.get_channel_name() is None
assert info.get_thumbnail() is None
assert info.get_title() is None
assert info.get_channel_id() is None
assert info.get_duration() is None

View File

@@ -0,0 +1,100 @@
{
"response": {
"responseContext": {
"webResponseContextExtensionData": ""
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [
{
"invalidationContinuationData": {
"invalidationId": {
"objectSource": 1000,
"objectId": "___objectId___",
"topic": "chat~00000000000~0000000",
"subscribeToGcmTopics": true,
"protoCreationTimestampMs": "1577804400000"
},
"timeoutMs": 10000,
"continuation": "___continuation___"
}
}
],
"actions": [
{
"addChatItemAction": {
"item": {
"liveChatMembershipItemRenderer": {
"id": "dummy_id",
"timestampUsec": 1570678496000000,
"authorExternalChannelId": "author_channel_id",
"headerSubtext": {
"runs": [
{
"text": "新規メンバー"
}
]
},
"authorName": {
"simpleText": "author_name"
},
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"authorBadges": [
{
"liveChatAuthorBadgeRenderer": {
"customThumbnail": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/X=s32-c-k"
},
{
"url": "https://yt3.ggpht.com/X=s64-c-k"
}
]
},
"tooltip": "新規メンバー",
"accessibility": {
"accessibilityData": {
"label": "新規メンバー"
}
}
}
}
],
"contextMenuEndpoint": {
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "___params___"
}
},
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
}
}
}
}
}
]
}
}
}
}

View File

@@ -0,0 +1,82 @@
{
"response": {
"responseContext": {
"webResponseContextExtensionData": ""
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [
{
"invalidationContinuationData": {
"invalidationId": {
"objectSource": 1000,
"objectId": "___objectId___",
"topic": "chat~00000000000~0000000",
"subscribeToGcmTopics": true,
"protoCreationTimestampMs": "1577804400000"
},
"timeoutMs": 10000,
"continuation": "___continuation___"
}
}
],
"actions": [
{
"addChatItemAction": {
"item": {
"liveChatLegacyPaidMessageRenderer": {
"id": "dummy_id",
"timestampUsec": 1570678496000000,
"eventText": {
"runs": [
{
"text": "新規メンバー"
}
]
},
"detailText": {
"simpleText": "ようこそ、author_name"
},
"authorName": {
"simpleText": "author_name"
},
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"authorExternalChannelId": "author_channel_id",
"contextMenuEndpoint": {
"clickTrackingParams": "___clickTrackingParams___",
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "___params___"
}
},
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
}
}
}
}
}
]
}
}
}
}

View File

@@ -0,0 +1,112 @@
{
"response": {
"responseContext": {
"webResponseContextExtensionData": "data"
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [
{
"liveChatReplayContinuationData": {
"invalidationId": {
"objectSource": 1000,
"objectId": "___objectId___",
"topic": "chat~00000000000~0000000",
"subscribeToGcmTopics": true,
"protoCreationTimestampMs": "1577804400000"
},
"timeoutMs": 10000,
"continuation": "___continuation___"
}
}
],
"actions": [
{
"replayChatItemAction": {
"actions": [
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"message": {
"runs": [
{
"text": "dummy_message"
}
]
},
"authorName": {
"simpleText": "author_name"
},
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"contextMenuEndpoint": {
"clickTrackingParams": "___clickTrackingParams___",
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "___params___"
}
},
"id": "dummy_id",
"timestampUsec": 1570678496000000,
"authorBadges": [
{
"liveChatAuthorBadgeRenderer": {
"customThumbnail": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/X=s16-c-k"
},
{
"url": "https://yt3.ggpht.com/X=s32-c-k"
}
]
},
"tooltip": "メンバー1 か月)",
"accessibility": {
"accessibilityData": {
"label": "メンバー1 か月)"
}
}
}
}
],
"authorExternalChannelId": "author_channel_id",
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
},
"timestampText": {
"simpleText": "1:23:45"
}
}
},
"clientId": "dummy_client_id"
}
}
],
"videoOffsetTimeMsec": "5025120"
}
}
]
}
}
}
}

184
tests/testdata/default/superchat.json vendored Normal file
View File

@@ -0,0 +1,184 @@
{
"response": {
"responseContext": {
"webResponseContextExtensionData": ""
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [
{
"invalidationContinuationData": {
"invalidationId": {
"objectSource": 1000,
"objectId": "___objectId___",
"topic": "chat~00000000000~0000000",
"subscribeToGcmTopics": true,
"protoCreationTimestampMs": "1577804400000"
},
"timeoutMs": 10000,
"continuation": "___continuation___"
}
}
],
"actions": [
{
"addChatItemAction": {
"item": {
"liveChatPaidMessageRenderer": {
"id": "dummy_id",
"timestampUsec": 1570678496000000,
"authorName": {
"simpleText": "author_name"
},
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"purchaseAmountText": {
"simpleText": "¥800"
},
"message": {
"runs": [
{
"text": "dummy_message"
}
]
},
"headerBackgroundColor": 4278239141,
"headerTextColor": 4278190080,
"bodyBackgroundColor": 4280150454,
"bodyTextColor": 4278190080,
"authorExternalChannelId": "author_channel_id",
"authorNameTextColor": 2315255808,
"contextMenuEndpoint": {
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "___params___"
}
},
"timestampColor": 2147483648,
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
}
}
}
}
},
{
"addLiveChatTickerItemAction": {
"item": {
"liveChatTickerPaidMessageItemRenderer": {
"id": "dummy_id",
"amount": {
"simpleText": "¥846"
},
"amountTextColor": 4278190080,
"startBackgroundColor": 4280150454,
"endBackgroundColor": 4278239141,
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"durationSec": 120,
"showItemEndpoint": {
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"showLiveChatItemEndpoint": {
"renderer": {
"liveChatPaidMessageRenderer": {
"id": "dummy_id",
"timestampUsec": 1570678496000000,
"authorName": {
"simpleText": "author_name"
},
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"purchaseAmountText": {
"simpleText": "¥846"
},
"message": {
"runs": [
{
"text": "dummy_message"
}
]
},
"headerBackgroundColor": 4278239141,
"headerTextColor": 4278190080,
"bodyBackgroundColor": 4280150454,
"bodyTextColor": 4278190080,
"authorExternalChannelId": "author_channel_id",
"authorNameTextColor": 2315255808,
"contextMenuEndpoint": {
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "___params___"
}
},
"timestampColor": 2147483648,
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
}
}
}
}
},
"authorExternalChannelId": "http://www.youtube.com/channel/author_channel_url",
"fullDurationSec": 120
}
},
"durationSec": "120"
}
}
]
}
}
}
}

View File

@@ -0,0 +1,99 @@
{
"response": {
"responseContext": {
"webResponseContextExtensionData": ""
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [
{
"invalidationContinuationData": {
"invalidationId": {
"objectSource": 1000,
"objectId": "___objectId___",
"topic": "chat~00000000000~0000000",
"subscribeToGcmTopics": true,
"protoCreationTimestampMs": "1577804400000"
},
"timeoutMs": 10000,
"continuation": "___continuation___"
}
}
],
"actions": [
{
"addChatItemAction": {
"item": {
"liveChatPaidStickerRenderer": {
"id": "dummy_id",
"contextMenuEndpoint": {
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "___params___"
}
},
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
},
"timestampUsec": 1570678496000000,
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"authorName": {
"simpleText": "author_name"
},
"authorExternalChannelId": "author_channel_id",
"sticker": {
"thumbnails": [
{
"url": "//lh3.googleusercontent.com/param_s=s72-rp",
"width": 72,
"height": 72
},
{
"url": "//lh3.googleusercontent.com/param_s=s144-rp",
"width": 144,
"height": 144
}
],
"accessibility": {
"accessibilityData": {
"label": "___sticker_label___"
}
}
},
"moneyChipBackgroundColor": 4278248959,
"moneyChipTextColor": 4278190080,
"purchaseAmountText": {
"simpleText": "¥200"
},
"stickerDisplayWidth": 72,
"stickerDisplayHeight": 72,
"backgroundColor": 4278237396,
"authorNameTextColor": 3003121664
}
}
}
}
]
}
}
}
}

79
tests/testdata/default/textmessage.json vendored Normal file
View File

@@ -0,0 +1,79 @@
{
"response": {
"responseContext": {
"webResponseContextExtensionData": ""
},
"continuationContents": {
"liveChatContinuation": {
"continuations": [
{
"invalidationContinuationData": {
"invalidationId": {
"objectSource": 1000,
"objectId": "___objectId___",
"topic": "chat~00000000000~0000000",
"subscribeToGcmTopics": true,
"protoCreationTimestampMs": "1577804400000"
},
"timeoutMs": 10000,
"continuation": "___continuation___"
}
}
],
"actions": [
{
"addChatItemAction": {
"item": {
"liveChatTextMessageRenderer": {
"message": {
"runs": [
{
"text": "dummy_message"
}
]
},
"authorName": {
"simpleText": "author_name"
},
"authorPhoto": {
"thumbnails": [
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s32-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 32,
"height": 32
},
{
"url": "https://yt3.ggpht.com/------------/AAAAAAAAAAA/AAAAAAAAAAA/xxxxxxxxxxxx/s64-x-x-xx-xx-xx-c0xffffff/photo.jpg",
"width": 64,
"height": 64
}
]
},
"contextMenuEndpoint": {
"commandMetadata": {
"webCommandMetadata": {
"ignoreNavigation": true
}
},
"liveChatItemContextMenuEndpoint": {
"params": "___params___"
}
},
"id": "dummy_id",
"timestampUsec": 1570678496000000,
"authorExternalChannelId": "author_channel_id",
"contextMenuAccessibility": {
"accessibilityData": {
"label": "コメントの操作"
}
}
}
},
"clientId": "dummy_client_id"
}
}
]
}
}
}
}