Archives/tubearchivist
2
0
Fork 0
mirror of https://github.com/tubearchivist/tubearchivist synced 2024-11-02 09:41:07 +00:00
Code Issues Projects Releases Wiki Activity

private methods for YoutubeSubtitle and SubtitleParser

Browse Source
This commit is contained in:
simon 2022-03-10 20:45:13 +07:00
parent 6e3df21f8c
commit d3e9646fb6
No known key found for this signature in database
GPG Key ID: 2C15AA5E89985DD4
1 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
tubearchivist/home/src/index/video.py
View File

@ -23,7 +23,7 @@ class YoutubeSubtitle:
self.video = video self.video = video
self.languages = False self.languages = False
def sub_conf_parse(self): def _sub_conf_parse(self):
"""add additional conf values to self""" """add additional conf values to self"""
languages_raw = self.video.config["downloads"]["subtitle"] languages_raw = self.video.config["downloads"]["subtitle"]
if languages_raw: if languages_raw:
@ -31,26 +31,26 @@ class YoutubeSubtitle:
def get_subtitles(self): def get_subtitles(self):
"""check what to do""" """check what to do"""
self.sub_conf_parse() self._sub_conf_parse()
if not self.languages: if not self.languages:
# no subtitles # no subtitles
return False return False
relevant_subtitles = [] relevant_subtitles = []
for lang in self.languages: for lang in self.languages:
user_sub = self.get_user_subtitles(lang) user_sub = self._get_user_subtitles(lang)
if user_sub: if user_sub:
relevant_subtitles.append(user_sub) relevant_subtitles.append(user_sub)
continue continue
if self.video.config["downloads"]["subtitle_source"] == "auto": if self.video.config["downloads"]["subtitle_source"] == "auto":
auto_cap = self.get_auto_caption(lang) auto_cap = self._get_auto_caption(lang)
if auto_cap: if auto_cap:
relevant_subtitles.append(auto_cap) relevant_subtitles.append(auto_cap)
return relevant_subtitles return relevant_subtitles
def get_auto_caption(self, lang): def _get_auto_caption(self, lang):
"""get auto_caption subtitles""" """get auto_caption subtitles"""
print(f"{self.video.youtube_id}-{lang}: get auto generated subtitles") print(f"{self.video.youtube_id}-{lang}: get auto generated subtitles")
all_subtitles = self.video.youtube_meta.get("automatic_captions") all_subtitles = self.video.youtube_meta.get("automatic_captions")
@ -87,7 +87,7 @@ class YoutubeSubtitle:
return all_subtitles return all_subtitles
def get_user_subtitles(self, lang): def _get_user_subtitles(self, lang):
"""get subtitles uploaded from channel owner""" """get subtitles uploaded from channel owner"""
print(f"{self.video.youtube_id}-{lang}: get user uploaded subtitles") print(f"{self.video.youtube_id}-{lang}: get user uploaded subtitles")
all_subtitles = self._normalize_lang() all_subtitles = self._normalize_lang()
@ -160,8 +160,8 @@ class SubtitleParser:
self.all_cues = [] self.all_cues = []
for idx, event in enumerate(all_events): for idx, event in enumerate(all_events):
cue = { cue = {
"start": self.ms_conv(event["tStartMs"]), "start": self._ms_conv(event["tStartMs"]),
"end": self.ms_conv(event["tStartMs"] + event["dDurationMs"]), "end": self._ms_conv(event["tStartMs"] + event["dDurationMs"]),
"text": "".join([i.get("utf8") for i in event["segs"]]), "text": "".join([i.get("utf8") for i in event["segs"]]),
"idx": idx + 1, "idx": idx + 1,
} }
@ -184,7 +184,7 @@ class SubtitleParser:
return flatten return flatten
@staticmethod @staticmethod
def ms_conv(ms): def _ms_conv(ms):
"""convert ms to timestamp""" """convert ms to timestamp"""
hours = str((ms // (1000 * 60 * 60)) % 24).zfill(2) hours = str((ms // (1000 * 60 * 60)) % 24).zfill(2)
minutes = str((ms // (1000 * 60)) % 60).zfill(2) minutes = str((ms // (1000 * 60)) % 60).zfill(2)
@ -206,7 +206,7 @@ class SubtitleParser:
def create_bulk_import(self, video, source): def create_bulk_import(self, video, source):
"""subtitle lines for es import""" """subtitle lines for es import"""
documents = self.create_documents(video, source) documents = self._create_documents(video, source)
bulk_list = [] bulk_list = []
for document in documents: for document in documents:
@ -220,9 +220,9 @@ class SubtitleParser:
return query_str return query_str
def create_documents(self, video, source): def _create_documents(self, video, source):
"""process documents""" """process documents"""
documents = self.chunk_list(video.youtube_id) documents = self._chunk_list(video.youtube_id)
channel = video.json_data.get("channel") channel = video.json_data.get("channel")
meta_dict = { meta_dict = {
"youtube_id": video.youtube_id, "youtube_id": video.youtube_id,
@ -238,7 +238,7 @@ class SubtitleParser:
return documents return documents
def chunk_list(self, youtube_id): def _chunk_list(self, youtube_id):
"""join cues for bulk import""" """join cues for bulk import"""
chunk_list = [] chunk_list = []