gh-mirrors/BaiduNetdisk-Docker
1
0
Fork 0
mirror of https://github.com/YuCat-OVO/BaiduNetdisk-Docker synced 2025-05-10 20:10:04 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Rewrite get_version

Browse Source
This commit is contained in:
YuCat 2024-05-04 23:40:46 +08:00
parent 962703a639
commit d13097ba39
9 changed files with 569 additions and 251 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
.github/workflows/build.yml vendored
View File

@ -8,22 +8,29 @@ on:
paths-ignore:
- ".github/**"
- "docs/**"
- "README.md"
- "**.md"
- "get_version.py"
env:
IMAGE_NAME: baidunetdisk-docker
DOCKERHUB_SLUG: crazymax/linguist
GHCR_SLUG: ghcr.io/yucat-ovo/baidunetdisk-docker
jobs:
Build:
name: Build
strategy:
matrix:
arch: [linux/amd64, linux/arm64]
outputs:
matrix: ${{ steps.platforms.outputs.matrix }}
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@master
- name: Create matrix
id: platforms
run: |
echo "matrix=$(docker buildx bake image-all --print | jq -cr '.target."image-all".platforms')" >>${GITHUB_OUTPUT}
- name: Set variables
id: set-vars
run: |

2
.gitignore vendored
View File

@ -1,3 +1,5 @@
.vscode/
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]

244
get_version.py
View File

@ -1,244 +0,0 @@
import json
import re
import time
import requests
from lxml import etree
GLOBAL_HEADER = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
}
# 截至2024-03-01最新的版本
GLOBAL_VERSION = [
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.11.5/baidunetdisk_4.11.5_amd64.deb",
]
# 定义需要检测的版本号范围
max_version = [4, 20, 0]
min_version = [4, 17, 0]
# 定义请求延时时间（秒）
GLOBAL_REQUEST_DELAY = 0.5
def get_js_url() -> str:
"""请求百度网盘下载页,获取存在下载链接的js文件"""
max_attempts = 5
attempt = 0
url = ""
while attempt < max_attempts:
try:
r = requests.get(
"https://pan.baidu.com/download",
headers=GLOBAL_HEADER,
)
e = etree.HTML(r.text, parser=None)
# 获取包含链接的js文件
for i in e.xpath("//script/@src"):
if re.search("https:\\/\\/.*chunk-common.*\\.js", i):
url = i
# print(url)
return url
except Exception as e:
print(f"An error occurred: {e}")
attempt += 1
time.sleep(1) # 等待1秒再重试
if attempt == max_attempts:
print("Failed after several attempts")
return url
def append_json(json_file_name: str, add):
"""为Json添加元素"""
file = None
try:
with open(json_file_name, "r") as f:
file = json.load(f)
# print("file=", file)
except FileNotFoundError:
file = json.loads("")
file.append(add)
# print("ufile=", u_file)
with open(json_file_name, "w") as f:
f.write(json.dumps(file, sort_keys=True, indent=4))
return
def parse_url_from_json() -> list:
l = ""
try:
with open("url.json", "r") as f:
l = json.load(f)
except FileNotFoundError:
l = []
return l
def parse_url_from_js():
"""从js文件中提取下载的链接并且去重,写入文件 url.json"""
url = get_js_url()
u_url = []
max_attempts = 5
attempt = 0
while attempt < max_attempts:
try:
d_url = ""
r = requests.get(
url,
headers=GLOBAL_HEADER,
)
# 过滤链接
d_url = re.findall(
'(?:link|url(?:_[0-9])?):"https://[a-zA-Z/\\.]*?/netdisk/[a-zA-Z10-9/\\._-]*?(?=")',
r.text,
)
# 清理
for i in range(len(d_url)):
d_url[i] = re.sub('(link|url(?:_[0-9])?):"', "", d_url[i])
# 去重
for i in d_url:
if i not in u_url:
u_url.append(i)
break
except Exception as e:
print(f"An error occurred: {e}")
attempt += 1
time.sleep(1) # 等待1秒再重试
if attempt == max_attempts:
print("Failed after several attempts,set url to default")
u_url = GLOBAL_VERSION
with open("url.json", "w") as f:
f.write(json.dumps(u_url, sort_keys=True, indent=4))
return
def make_info_json(urls: list):
"""保存为Json文件"""
# print("urls:", urls)
l_url = urls[-3:]
# print(l_url)
j = []
for i in l_url:
j.append(
{
"version": re.findall("(?<=/)((?:[0-9]{1,2}(?:\\.)?){1,3})(?=/)", i)[0],
"arch": re.findall("(amd64|arm64|x86_64)", i)[0],
"pak": re.findall("(rpm|deb)", i)[0],
"url": i,
},
)
# print(j)
with open("info.json", "w") as f:
f.write(json.dumps(j, sort_keys=True, indent=4))
return
def make_url_temple(arch: str):
"""按照之前所获取的 url.json,创建模板"""
l = ""
url_temple = ""
try:
with open("url.json", "r") as f:
l = json.load(f)
for i in l:
if re.search("amd64", i) != None and re.search("deb", i) != None:
url_temple = re.sub("amd64", arch, i)
url_temple = re.sub(
"(?<=[_/])((?:[0-9]{1,2}(?:\\.)?){1,3})(?=[_/])", "{0}", url_temple
)
break
# print(url_temple)
except FileNotFoundError:
url_temple = "https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/{0}/baidunetdisk_{0}_arm64.deb"
# print(url_temple)
return url_temple
def check_version(version: list, arch: str):
"""检测指定版本号是否可用"""
url = make_url_temple(arch).format(".".join(str(v) for v in version))
# url = "https://httpbin.org/status/200"
# print("Getting {0}".format(url))
max_attempts = 5
attempt = 0
while attempt < max_attempts:
try:
response = requests.head(
url,
headers=GLOBAL_HEADER,
)
if response.status_code == 200:
return True
else:
return False
except Exception as e:
print(f"An error occurred: {e}")
attempt += 1
time.sleep(1) # 等待1秒再重试
if attempt == max_attempts:
print("Failed after several attempts")
return
def find_latest_version(min_version, max_version):
"""寻找最新版本号"""
version_list = [
[x, y, z]
for x in range(max_version[0], min_version[0] - 1, -1)
for y in range(max_version[1], min_version[1] - 1, -1)
for z in range(20, -1, -1)
if not (x == max_version[0] and y == max_version[1] and z > max_version[2])
if not (x == min_version[0] and y == min_version[1] and z < min_version[2])
]
for arch in ["amd64", "arm64"]:
for version in version_list:
# 检测指定版本号是否可用
if check_version(version, arch):
print(
"arch {0} version {1} is available".format(
arch, ".".join(str(v) for v in version)
)
)
append_json(
"url.json",
make_url_temple(arch).format(".".join(str(v) for v in version)),
)
time.sleep(GLOBAL_REQUEST_DELAY)
break
else:
print(
"arch {0} version {1} is not available".format(
arch, ".".join(str(v) for v in version)
)
)
time.sleep(GLOBAL_REQUEST_DELAY)
# 找不到可用版本号，返回None
return None
if __name__ == "__main__":
parse_url_from_js()
find_latest_version(min_version, max_version)
urls = parse_url_from_json()
make_info_json(urls)

42
jsontemplate.json Normal file
View File

@ -0,0 +1,42 @@
{
"platform": {
"linux": {
"latest": {
"version": "4.17.7",
"amd64": "amd64url",
"arm64": "arm64url"
},
"4.17.7": {
"amd64": "amd64url",
"arm64": "arm64url"
},
"4.11.5": {
"amd64": "amd64url",
"arm64": "arm64url"
}
},
"windows": {
"latest": {
"version": "7.19.0.18",
"amd64": "amd64url"
},
"7.19.0.18": {
"amd64": "amd64url"
},
"6.9.10.1": {
"amd64": "amd64url"
}
},
"mac": {
"latest": {
"version": "4.11.0",
"amd64": "amd64url",
"arm64": "arm64url"
},
"4.11.0": {
"amd64": "amd64url",
"arm64": "arm64url"
}
}
}
}

81
scripts/api_fetcher.py Normal file
View File

@ -0,0 +1,81 @@
import asyncio
import json
import random
import re
import httpx
class APIFetcher:
def __init__(self) -> None:
uas = [
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36 Edg/121.0.0.0",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:123.0) Gecko/20100101 Firefox/123.0",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
]
self.ua = random.choice(uas)
async def async_fetcher(self, platform: str, max_attempt: int = 5) -> str | None:
url = "https://yun.baidu.com/disk/cmsdata?platform={0}&page=1&num=100".format(
platform
)
for _ in range(max_attempt):
try:
async with httpx.AsyncClient() as client:
response = await client.get(
url,
headers={
"User-Agent": self.ua,
"Referer": "https://yun.baidu.com/disk/version?errmsg=Auth+Login+Sucess&errno=0&ssnerror=0&",
},
timeout=10,
)
return response.text
except httpx.HTTPError as e:
print(f"An error occurred: {e}")
print(f"Fetch {0} failed after several attempts", url)
return None
def linux_version(self):
doc = self.linux_json
version = json.loads(doc)["list"][0]["version"]
version = re.search(r"(?P<version>([0-9]{1,2}(\.)?){3,4})", version).group(
"version"
)
return version
def windows_version(self):
doc = self.windows_json
version = json.loads(doc)["list"][0]["version"]
version = re.search(r"(?P<version>([0-9]{1,2}(\.)?){3,4})", version).group(
"version"
)
return version
def mac_version(self):
doc = self.mac_json
version = json.loads(doc)["list"][0]["version"]
version = re.search(r"(?P<version>([0-9]{1,2}(\.)?){3,4})", version).group(
"version"
)
return version
async def run(self):
L = await asyncio.gather(
self.async_fetcher("linux"),
self.async_fetcher("windows"),
self.async_fetcher("mac"),
)
# print(L)
self.linux_json, self.windows_json, self.mac_json = L
print(self.linux_json)
if __name__ == "__main__":
import doctest
doctest.testmod()
af = APIFetcher()
af.run()

146
scripts/get_version.py Normal file
View File

@ -0,0 +1,146 @@
import json
import re
import time
import requests
class LinkObj:
def __init__(self, link: str) -> None:
self.link = link
self.version, self.pkg = re.search(
r"(?P<version>([0-9]{1,2}(\.)?){3,4}(?=[\._/])).*(?P<pkg>(?<=\.)[a-z]{3,4}$)",
link,
).group("version", "pkg")
arch = re.search(
r"(?P<arch>amd64|arm64)",
link,
)
if arch:
self.arch = arch.group("arch")
else:
self.arch = "amd64"
class Version:
def __init__(self, version, arch_links):
self.version = version
self.arch_links = arch_links
def to_dict(self):
return self.arch_links.copy()
class Platform:
def __init__(self) -> None:
pass
def append_json(json_file_name: str, add):
"""为Json添加元素"""
file = None
try:
with open(json_file_name, "r") as f:
file = json.load(f)
# print("file=", file)
except FileNotFoundError:
file = json.loads("")
file.append(add)
# print("ufile=", u_file)
with open(json_file_name, "w") as f:
f.write(json.dumps(file, sort_keys=True, indent=4))
return
def parse_url_from_json() -> list:
link = ""
try:
with open("url.json", "r") as f:
link = json.load(f)
except FileNotFoundError:
link = []
return link
def make_info_json(urls: list):
"""保存为Json文件"""
# print("urls:", urls)
l_url = urls[-3:]
# print(l_url)
j = []
for i in l_url:
j.append(
{
"version": re.findall("(?<=/)((?:[0-9]{1,2}(?:\\.)?){1,3})(?=/)", i)[0],
"arch": re.findall("(amd64|arm64|x86_64)", i)[0],
"pak": re.findall("(rpm|deb)", i)[0],
"url": i,
},
)
# print(j)
with open("info.json", "w") as f:
f.write(json.dumps(j, sort_keys=True, indent=4))
return
def make_url_temple(arch: str):
"""按照之前所获取的 url.json,创建模板"""
link = ""
url_temple = ""
try:
with open("url.json", "r") as f:
link = json.load(f)
for i in link:
if re.search("amd64", i) is not None and re.search("deb", i) is not None:
url_temple = re.sub("amd64", arch, i)
url_temple = re.sub(
"(?<=[_/])((?:[0-9]{1,2}(?:\\.)?){1,3})(?=[_/])", "{0}", url_temple
)
break
# print(url_temple)
except FileNotFoundError:
url_temple = "https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/{0}/baidunetdisk_{0}_arm64.deb"
# print(url_temple)
return url_temple
def check_version(version: list, arch: str):
"""检测指定版本号是否可用"""
url = make_url_temple(arch).format(".".join(str(v) for v in version))
# url = "https://httpbin.org/status/200"
# print("Getting {0}".format(url))
max_attempts = 5
attempt = 0
while attempt < max_attempts:
try:
response = requests.head(
url,
headers="",
)
if response.status_code == 200:
return True
else:
return False
except Exception as e:
print(f"An error occurred: {e}")
attempt += 1
time.sleep(1) # 等待1秒再重试
if attempt == max_attempts:
print("Failed after several attempts")
return
def main():
pass
if __name__ == "__main__":
main()

138
scripts/version_finder Normal file
View File

@ -0,0 +1,138 @@
import re
from api_fetcher import APIFetcher
class VersionFinder:
def __init__(self) -> None:
pass
class TemplateGenerator:
"""模板创建类
Args: 从网页获取的url数组
Returns: 模板数组, 版本区域由{0}替代
"""
def __init__(self, urls: list) -> list[str]:
self.linux_link = []
self.windows_link = ""
self.mac_link = []
for i in urls:
if re.search("(deb|rpm)", i) is not None:
self.linux_link.append(i)
elif re.search("exe", i) is not None:
if self.windows_link != "":
continue
self.windows_link = i
elif re.search("dmg", i) is not None:
self.mac_link.append(i)
def linux(self):
arch = ["arm64", "amd64"]
url_template = []
for url in self.linux_link:
# print(url)
version = re.search(
r"(?P<version>(?<=[_/])((?:[0-9]{1,2}(?:\.)?){1,3})(?=[_/])).*(?P<pkg>(?<=\.)[a-z]{3,4}$)",
url,
).group("pkg", "version")
self.linux_version = version[1]
if version[0] == "rpm":
url_template.append(re.sub(version[1], "{0}", url))
else:
template = re.sub("amd64", "{0}", url)
url_template += [
re.sub(version[1], "{0}", template.format(i)) for i in arch
]
return url_template
def windows(self):
self.windows_version = re.search(
r"(?P<version>([0-9]{1,2}(\.)?){3,4}(?=\.|_|\/))", self.windows_link
).group("version")
return re.sub(self.windows_version, "{0}", self.windows_link)
def mac(self):
versions = {}
url_template = []
for url in self.mac_link:
version = re.search(
r"(?P<version>(?<=[_])((?:[0-9]{1,2}(?:\.)?){1,3})(?=[_\.]))",
url,
).group("version")
if re.search("arm", url):
versions["arm"] = version
url_template.append(re.sub(version, "{0}", url))
else:
versions["amd"] = version
url_template.append(re.sub(version, "{0}", url))
self.mac_version = versions
return url_template
def __version_compear(a: str, b: str):
a_split = a.split(".")
b_split = b.split(".")
flag = False
if len(a) == len(b):
length = len(a_split)
for i in range(length):
if a_split[i] > b_split[i]:
flag = True
if flag:
return a
else:
return b
else:
print("The two version numbers have different lengths.")
return a
def version_setter(self, api_version):
self.linux_version = self.__version_compear(
self.linux_version, api_version.linux_version()
)
self.windows_version = self.__version_compear(
self.windows_version, api_version.windows_version()
)
self.mac_version = self.__version_compear(
self.mac_version, api_version.mac_version()
)
def run(self, urls: list):
tg = self.TemplateGenerator(urls)
linux_template = tg.linux()
windows_template = tg.windows()
mac_template = tg.mac()
self.linux_version = tg.linux_version
self.windows_version = tg.windows_version
self.mac_version = tg.mac_version
api = APIFetcher()
api.run()
self.version_setter(api)
def append_json(self):
pass
if __name__ == "__main__":
# import doctest
# doctest.testmod()
urls = [
"https://issuepcdn.baidupcs.com/issue/netdisk/yunguanjia/BaiduNetdisk_7.19.0.18.exe",
"https://issuepcdn.baidupcs.com/issue/netdisk/yunguanjia/BaiduNetdisk_6.9.10.1.exe",
"https://issuepcdn.baidupcs.com/issue/netdisk/MACguanjia/BaiduNetdisk_mac_4.11.0.dmg",
"https://issuepcdn.baidupcs.com/issue/netdisk/MACguanjia/BaiduNetdisk_mac_4.11.0_arm64.dmg",
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.11.5/baidunetdisk-4.11.5.x86_64.rpm",
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.11.5/baidunetdisk_4.11.5_amd64.deb",
]
vf = VersionFinder()
vf.run(urls)
print(vf.linux_version)
pass

148
scripts/web_fetcher.py Normal file
View File

@ -0,0 +1,148 @@
import json
import random
import re
import httpx
from lxml import etree
class WebFetcher:
def __init__(self) -> None:
uas = [
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36 Edg/121.0.0.0",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:123.0) Gecko/20100101 Firefox/123.0",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
]
self.ua = random.choice(uas)
def fetcher(self, url: str, max_attempt: int = 5) -> str | None:
"""网址抓取器
从给定 url 抓取对应数据, 失败时重试, 默认重试5次
>>> bdnd = WebFetcher()
>>> type(bdnd.fetcher("https://pan.baidu.com/download")) is str
True
>>> type(bdnd.fetcher("https://1.1.1.1", max_attempt=1)) is str
True
>>> bdnd.fetcher("https://172.1.1.1", max_attempt=1)
An error occurred: timed out
Args:
url: 网址
max_attempt: 重试次数
Returns:
成功时返回所获取网页的text数据
失败时返回None
"""
for _ in range(max_attempt):
try:
response = httpx.get(
url,
headers={
"User-Agent": self.ua,
"Referer": "https://pan.baidu.com/disk/main",
},
timeout=10,
)
return response.text
except httpx.HTTPError as e:
print(f"An error occurred: {e}")
async def async_fetcher(self, url: str, max_attempt: int = 5) -> str | None:
for attempt in range(max_attempt):
try:
async with httpx.AsyncClient() as client:
response = await client.get(
url,
headers={
"User-Agent": self.ua,
"Referer": "https://pan.baidu.com/disk/main",
},
timeout=10,
)
return response
except httpx.HTTPError as e:
print(f"An error occurred: {e}")
print(f"Fetch {0} failed after several attempts", url)
return None
def fetch_js_url(self) -> list:
"""请求百度网盘下载页,获取存在下载链接的js文件
Returns:
成功时设置self.js_url为所获取网页的text数据
失败时设置self.js_url为None
>>> bdnd = WebFetcher()
>>> bdnd.fetch_js_url()
'https://nd-static.bdstatic.com/m-static/wp-brand/js/chunk-common.8b953c6c.js'
"""
response = self.fetcher("https://pan.baidu.com/download")
if response is not None:
try:
doc = etree.HTML(response, parser=None)
for i in doc.xpath("//script/@src"):
if re.search(r"https:\/\/.*chunk-common.*\.js", i):
self.js_url = i
return i
except Exception as e:
print(f"An error occurred: {e}, set js_url to default")
self.js_url = "https://nd-static.bdstatic.com/m-static/wp-brand/js/chunk-common.8b953c6c.js"
return self.js_url
else:
print("Fetcher return None, set js_url to default")
self.js_url = "https://nd-static.bdstatic.com/m-static/wp-brand/js/chunk-common.8b953c6c.js"
return self.js_url
def parse_url_from_js(self) -> list:
"""从js文件中提取下载的链接并且去重
>>> bdnd = WebFetcher()
>>> bdnd.fetch_js_url()
'https://nd-static.bdstatic.com/m-static/wp-brand/js/chunk-common.8b953c6c.js'
>>> len(bdnd.parse_url_from_js())
6
"""
# 获取js数据
js_url = self.js_url
response = self.fetcher(js_url)
# 过滤链接
original_url = re.findall(
r'(?:(?:link|url)(?:_[0-9])?:")(?P<link>https://[a-zA-Z/\.]*?/netdisk/[a-zA-Z10-9/\._-]*?)(?=")',
response,
)
# 去重
unique_url = []
for i in original_url:
if i not in unique_url:
unique_url.append(i)
self.link_url = unique_url
return unique_url
def json_saver(self):
try:
with open("url.json", "w") as f:
f.write(json.dumps(self.link_url, sort_keys=True, indent=4))
except Exception as e:
print(f"An error occurred: {e}, Please check the permissions.")
def run(self):
doc = WebFetcher()
doc.fetch_js_url()
doc.parse_url_from_js()
doc.json_saver()
return self.link_url
def get_urls(self) -> list:
return self.link_url
if __name__ == "__main__":
import doctest
doctest.testmod()

4
url.json
View File

@ -4,7 +4,5 @@
"https://issuepcdn.baidupcs.com/issue/netdisk/MACguanjia/BaiduNetdisk_mac_4.11.0.dmg",
"https://issuepcdn.baidupcs.com/issue/netdisk/MACguanjia/BaiduNetdisk_mac_4.11.0_arm64.dmg",
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.11.5/baidunetdisk-4.11.5.x86_64.rpm",
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.11.5/baidunetdisk_4.11.5_amd64.deb",
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.17.7/baidunetdisk_4.17.7_amd64.deb",
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.17.7/baidunetdisk_4.17.7_arm64.deb"
"https://issuepcdn.baidupcs.com/issue/netdisk/LinuxGuanjia/4.11.5/baidunetdisk_4.11.5_amd64.deb"
]