ramforth/pytchat-fork
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into feature/httpx

Browse Source
This commit is contained in:
taizan-hokuto
2020-08-22 12:41:57 +09:00
parent 5f78a99507 f9480ea1eb
commit 8012e1d191
5 changed files with 15 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pytchat/__init__.py
View File

@@ -2,7 +2,7 @@
pytchat is a lightweight python library to browse youtube livechat without Selenium or BeautifulSoup. pytchat is a lightweight python library to browse youtube livechat without Selenium or BeautifulSoup.
""" """
__copyright__ = 'Copyright (C) 2019 taizan-hokuto' __copyright__ = 'Copyright (C) 2019 taizan-hokuto'
__version__ = '0.1.3' __version__ = '0.1.4'
__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'

8
pytchat/cli/__init__.py
View File

@@ -3,7 +3,7 @@ import os
from pathlib import Path from pathlib import Path
from pytchat.util.extract_video_id import extract_video_id from pytchat.util.extract_video_id import extract_video_id
from .arguments import Arguments from .arguments import Arguments
from .. exceptions import InvalidVideoIdException, NoContents from .. exceptions import InvalidVideoIdException, NoContents, VideoInfoParseException
from .. processors.html_archiver import HTMLArchiver from .. processors.html_archiver import HTMLArchiver
from .. tool.extract.extractor import Extractor from .. tool.extract.extractor import Extractor
from .. tool.videoinfo import VideoInfo from .. tool.videoinfo import VideoInfo
@@ -40,11 +40,11 @@ def main():
if '[' in video_id: if '[' in video_id:
video_id = video_id.replace('[', '').replace(']', '') video_id = video_id.replace('[', '').replace(']', '')
try: try:
video_id = extract_video_id(video_id)
if os.path.exists(Arguments().output): if os.path.exists(Arguments().output):
path = Path(Arguments().output + video_id + '.html') path = Path(Arguments().output + video_id + '.html')
else: else:
raise FileNotFoundError raise FileNotFoundError
video_id = extract_video_id(video_id)
info = VideoInfo(video_id) info = VideoInfo(video_id)
print(f"Extracting...\n" print(f"Extracting...\n"
f" video_id: {video_id}\n" f" video_id: {video_id}\n"
@@ -63,7 +63,9 @@ def main():
except (TypeError, NoContents) as e: except (TypeError, NoContents) as e:
print(e) print(e)
except FileNotFoundError: except FileNotFoundError:
print("The specified directory does not exist.:{}".format(Arguments().output )) print("The specified directory does not exist.:{}".format(Arguments().output))
except VideoInfoParseException:
print("Cannot parse video information.:{}".format(video_id))
return return
parser.print_help() parser.print_help()

6
pytchat/exceptions.py
View File

@@ -62,3 +62,9 @@ class ReceivedUnknownContinuation(ChatParseException):
class FailedExtractContinuation(ChatDataFinished): class FailedExtractContinuation(ChatDataFinished):
pass pass
class VideoInfoParseException(Exception):
'''
thrown when failed to parse video info
'''

2
pytchat/tool/extract/extractor.py
View File

@@ -79,7 +79,7 @@ class Extractor:
def extract(self): def extract(self):
if self.duration == 0: if self.duration == 0:
print("video is not archived.") print("\nCannot extract chat data:\n The specified video has not yet been archived.")
return [] return []
data = self._execute_extract_operations() data = self._execute_extract_operations()
if self.processor is None: if self.processor is None:

4
pytchat/tool/videoinfo.py
View File

@@ -7,7 +7,7 @@ from ..util.extract_video_id import extract_video_id
headers = config.headers headers = config.headers
pattern = re.compile(r"yt\.setConfig\({'PLAYER_CONFIG': ({.*})}\);") pattern = re.compile(r"'PLAYER_CONFIG': ({.*}}})")
item_channel_id = [ item_channel_id = [
"videoDetails", "videoDetails",
@@ -91,7 +91,7 @@ class VideoInfo:
def _parse(self, text): def _parse(self, text):
result = re.search(pattern, text) result = re.search(pattern, text)
res = json.loads(result.group(1)) res = json.loads(result.group(1)[:-1])
response = self._get_item(res, item_response) response = self._get_item(res, item_response)
if response is None: if response is None:
self._check_video_is_private(res.get("args")) self._check_video_is_private(res.get("args"))