GithubBackup/MoviePilot
1
0
Fork 0
mirror of https://github.com/jxxghp/MoviePilot.git synced 2026-06-12 19:21:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add Rust acceleration for core parsing

Browse Source
This commit is contained in:
jxxghp
2026-05-22 19:57:26 +08:00
parent 7daeb17d85
commit bd4d493f34
28 changed files with 5012 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
app/modules/indexer/parser/__init__.py
View File

@@ -11,8 +11,10 @@ from requests import Session
from app.core.config import settings
from app.helper.cloudflare import under_challenge
from app.log import logger
from app.utils import rust_accel
from app.utils.http import RequestUtils
from app.utils.site import SiteUtils
from app.utils.string import StringUtils
# 站点框架
@@ -154,6 +156,16 @@ class SiteParserBase(metaclass=ABCMeta):
"""
return self.schema
@staticmethod
def num_filesize(text) -> int:
"""
将站点页面中的文件大小文本转换为字节，优先使用 Rust 快路径。
"""
rust_value = rust_accel.parse_filesize(text)
if rust_value is not None:
return rust_value
return StringUtils.num_filesize(text)
def parse(self):
"""
解析站点信息

10
app/modules/indexer/parser/nexus_php.py
View File

@@ -93,10 +93,10 @@ class NexusPhpSiteUserInfo(SiteParserBase):
html_text = self._prepare_html_text(html_text)
upload_match = re.search(r"[^总]上[传傳]量?[:：_<>/a-zA-Z-=\"'\s#;]+([\d,.\s]+[KMGTPI]*B)", html_text,
re.IGNORECASE)
self.upload = StringUtils.num_filesize(upload_match.group(1).strip()) if upload_match else 0
self.upload = self.num_filesize(upload_match.group(1).strip()) if upload_match else 0
download_match = re.search(r"[^总子影力]下[载載]量?[:：_<>/a-zA-Z-=\"'\s#;]+([\d,.\s]+[KMGTPI]*B)", html_text,
re.IGNORECASE)
self.download = StringUtils.num_filesize(download_match.group(1).strip()) if download_match else 0
self.download = self.num_filesize(download_match.group(1).strip()) if download_match else 0
ratio_match = re.search(r"分享率[:：_<>/a-zA-Z-=\"'\s#;]+([\d,.\s]+)", html_text)
# 计算分享率
calc_ratio = 0.0 if self.download <= 0.0 else round(self.upload / self.download, 3)
@@ -209,7 +209,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
page_seeding = len(seeding_sizes)
for i in range(0, len(seeding_sizes)):
size = StringUtils.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
size = self.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
seeders = StringUtils.str_int(seeding_seeders[i])
page_seeding_size += size
@@ -273,7 +273,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
tmp_seeding_size = 0
tmp_seeding_info = []
for i in range(0, len(seeding_sizes)):
size = StringUtils.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
size = self.num_filesize(seeding_sizes[i].xpath("string(.)").strip())
seeders = StringUtils.str_int(seeding_seeders[i])
tmp_seeding_size += size
@@ -292,7 +292,7 @@ class NexusPhpSiteUserInfo(SiteParserBase):
seeding_size_match = re.search(r"总做种体积:\s+([\d,.\s]+[KMGTPI]*B)", seeding_sizes[0], re.IGNORECASE)
tmp_seeding = StringUtils.str_int(seeding_match.group(1)) if (
seeding_match and seeding_match.group(1)) else 0
tmp_seeding_size = StringUtils.num_filesize(
tmp_seeding_size = self.num_filesize(
seeding_size_match.group(1).strip()) if seeding_size_match else 0
if not self.seeding_size:
self.seeding_size = tmp_seeding_size

8
app/modules/indexer/parser/zhixing.py
View File

@@ -75,7 +75,7 @@ class ZhixingSiteUserInfo(SiteParserBase):
s = s.strip()
if re.match(r'^\d+(\.\d+)?$', s):
s += ' B'
return StringUtils.num_filesize(s) if s else 0
return self.num_filesize(s) if s else 0
self.upload = num_filesize_safe(info_dict.get('上传流量')) if '上传流量' in info_dict else 0
self.download = num_filesize_safe(info_dict.get('下载流量')) if '下载流量' in info_dict else 0
@@ -108,7 +108,7 @@ class ZhixingSiteUserInfo(SiteParserBase):
if size_td:
size_text = size_td.find('a').text if size_td.find('a') else size_td.text.strip()
page_seeding += 1
page_seeding_size += StringUtils.num_filesize(size_text)
page_seeding_size += self.num_filesize(size_text)
return page_seeding, page_seeding_size
def _parse_message_unread_links(self, html_text: str, msg_links: list) -> Optional[str]:
@@ -164,7 +164,7 @@ class ZhixingSiteUserInfo(SiteParserBase):
s = s.strip()
if re.match(r'^\d+(\.\d+)?$', s):
s += ' B'
return StringUtils.num_filesize(s) if s else 0
return self.num_filesize(s) if s else 0
self.seeding = int(self._basic_info.get('当前保种数量', 0))
self.seeding_size = num_filesize_safe(self._basic_info.get('当前保种容量', ''))
@@ -181,4 +181,4 @@ class ZhixingSiteUserInfo(SiteParserBase):
self.message_unread = str(self.message_unread or 0)
self.seeding = str(self.seeding or 0)
self.seeding_size = str(self.seeding_size or 0)
self.seeding_size = str(self.seeding_size or 0)