torrent-tracker-search 0.2.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- torrent_tracker_search-0.2.0/PKG-INFO +52 -0
- torrent_tracker_search-0.2.0/README.md +33 -0
- torrent_tracker_search-0.2.0/pyproject.toml +17 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/ClientBuilder.py +20 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/__init__.py +0 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/common/TrackerClient.py +19 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/common/TrackerRequestException.py +3 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/common/TrackerResponse.py +25 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/common/__init__.py +0 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/__init__.py +0 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/NNMClubClient.py +47 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/NNMClubService.py +72 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/NNMClubURL.py +15 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/__init__.py +0 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/NNMClubAuthorLink.py +7 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/NNMClubForumLink.py +7 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/NNMClubSearchItem.py +18 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/NNMClubTopicLink.py +7 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/NNMClubTorrentFile.py +10 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/NNMClubTorrentItem.py +14 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/__init__.py +0 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/NNMClubBBCodeParser.py +15 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/NNMClubSearchParser.py +55 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/NNMClubTorrentFilesParser.py +96 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/NNMClubTorrentParser.py +30 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/__init__.py +25 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/RuTrackerClient.py +47 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/RuTrackerService.py +98 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/RuTrackerURL.py +16 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/__init__.py +0 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/RuTrackerAuthorLink.py +7 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/RuTrackerForumLink.py +7 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/RuTrackerSearchItem.py +21 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/RuTrackerTorrentFile.py +9 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/RuTrackerTorrentItem.py +14 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/__init__.py +0 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/parser/RuTrackerSearchParser.py +54 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/parser/RuTrackerTorrentFilesParser.py +57 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/parser/RuTrackerTorrentParser.py +32 -0
- torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/parser/__init__.py +23 -0
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
Metadata-Version: 2.3
|
|
2
|
+
Name: torrent-tracker-search
|
|
3
|
+
Version: 0.2.0
|
|
4
|
+
Summary: Torrent Tracker Search Lib
|
|
5
|
+
Home-page: https://gitlab.com/Bitnik212/torrent-tracker-search
|
|
6
|
+
License: MIT
|
|
7
|
+
Author: Николай Витальевич Никоноров
|
|
8
|
+
Author-email: nnv@bitt.moe
|
|
9
|
+
Requires-Python: >=3.10.16,<4.0.0
|
|
10
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
11
|
+
Classifier: Programming Language :: Python :: 3
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
15
|
+
Requires-Dist: aiohttp (==3.11.11)
|
|
16
|
+
Requires-Dist: beautifulsoup4 (==4.12.3)
|
|
17
|
+
Project-URL: Repository, https://gitlab.com/Bitnik212/torrent-tracker-search
|
|
18
|
+
Description-Content-Type: text/markdown
|
|
19
|
+
|
|
20
|
+
# Torrent Tracker Search Lib
|
|
21
|
+
|
|
22
|
+
## Integrations
|
|
23
|
+
|
|
24
|
+
- rutracker.org
|
|
25
|
+
- nnmclub.to
|
|
26
|
+
|
|
27
|
+
## Example
|
|
28
|
+
|
|
29
|
+
```python
|
|
30
|
+
from torrent_tracker_search.ClientBuilder import ClientBuilder
|
|
31
|
+
from torrent_tracker_search.source.rutracker.RuTrackerService import RuTrackerService
|
|
32
|
+
from torrent_tracker_search.source.rutracker.RuTrackerClient import RuTrackerClient
|
|
33
|
+
from torrent_tracker_search.source.nnmclub.NNMClubService import NNMClubService
|
|
34
|
+
from torrent_tracker_search.source.nnmclub.NNMClubClient import NNMClubClient
|
|
35
|
+
|
|
36
|
+
builder = ClientBuilder()
|
|
37
|
+
rutracker_client, nnmclub_client = builder.build(clients=[RuTrackerClient(), NNMClubClient()])
|
|
38
|
+
rutracker_service = RuTrackerService(rutracker_client)
|
|
39
|
+
nnmclub_service = NNMClubService(rutracker_client)
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
async def main(query: str):
|
|
43
|
+
await rutracker_service.login(login="", password="")
|
|
44
|
+
nnmclub_service.login(session_id="")
|
|
45
|
+
result_from_rutracker = await rutracker_service.search(query)
|
|
46
|
+
result_from_nnmclub = await nnmclub_service.search(query)
|
|
47
|
+
print(f"{result_from_rutracker=}")
|
|
48
|
+
print(f"{result_from_nnmclub=}")
|
|
49
|
+
await builder.session.close()
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
```
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
# Torrent Tracker Search Lib
|
|
2
|
+
|
|
3
|
+
## Integrations
|
|
4
|
+
|
|
5
|
+
- rutracker.org
|
|
6
|
+
- nnmclub.to
|
|
7
|
+
|
|
8
|
+
## Example
|
|
9
|
+
|
|
10
|
+
```python
|
|
11
|
+
from torrent_tracker_search.ClientBuilder import ClientBuilder
|
|
12
|
+
from torrent_tracker_search.source.rutracker.RuTrackerService import RuTrackerService
|
|
13
|
+
from torrent_tracker_search.source.rutracker.RuTrackerClient import RuTrackerClient
|
|
14
|
+
from torrent_tracker_search.source.nnmclub.NNMClubService import NNMClubService
|
|
15
|
+
from torrent_tracker_search.source.nnmclub.NNMClubClient import NNMClubClient
|
|
16
|
+
|
|
17
|
+
builder = ClientBuilder()
|
|
18
|
+
rutracker_client, nnmclub_client = builder.build(clients=[RuTrackerClient(), NNMClubClient()])
|
|
19
|
+
rutracker_service = RuTrackerService(rutracker_client)
|
|
20
|
+
nnmclub_service = NNMClubService(rutracker_client)
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
async def main(query: str):
|
|
24
|
+
await rutracker_service.login(login="", password="")
|
|
25
|
+
nnmclub_service.login(session_id="")
|
|
26
|
+
result_from_rutracker = await rutracker_service.search(query)
|
|
27
|
+
result_from_nnmclub = await nnmclub_service.search(query)
|
|
28
|
+
print(f"{result_from_rutracker=}")
|
|
29
|
+
print(f"{result_from_nnmclub=}")
|
|
30
|
+
await builder.session.close()
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
```
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
[tool.poetry]
|
|
2
|
+
name = "torrent-tracker-search"
|
|
3
|
+
version = "0.2.0"
|
|
4
|
+
description = "Torrent Tracker Search Lib"
|
|
5
|
+
authors = ["Николай Витальевич Никоноров <nnv@bitt.moe>"]
|
|
6
|
+
license = "MIT"
|
|
7
|
+
readme = "README.md"
|
|
8
|
+
repository = "https://gitlab.com/Bitnik212/torrent-tracker-search"
|
|
9
|
+
|
|
10
|
+
[tool.poetry.dependencies]
|
|
11
|
+
python = "^3.10.16"
|
|
12
|
+
aiohttp = "3.11.11"
|
|
13
|
+
beautifulsoup4 = "4.12.3"
|
|
14
|
+
|
|
15
|
+
[build-system]
|
|
16
|
+
requires = ["poetry-core"]
|
|
17
|
+
build-backend = "poetry.core.masonry.api"
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
from typing import List, Optional, Final, Dict
|
|
2
|
+
|
|
3
|
+
from aiohttp import ClientSession
|
|
4
|
+
|
|
5
|
+
from torrent_tracker_search.common.TrackerClient import TrackerClient
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class ClientBuilder:
|
|
9
|
+
|
|
10
|
+
DEFAULT_HEADERS: Final[Dict[str, str]] = {
|
|
11
|
+
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
|
|
12
|
+
}
|
|
13
|
+
|
|
14
|
+
def __init__(self, session: Optional[ClientSession] = None):
|
|
15
|
+
self.session: ClientSession = session or ClientSession(headers=self.DEFAULT_HEADERS)
|
|
16
|
+
|
|
17
|
+
def build(self, clients: List[TrackerClient]) -> List[TrackerClient]:
|
|
18
|
+
for client in clients:
|
|
19
|
+
client.session = self.session
|
|
20
|
+
return clients
|
|
File without changes
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
from typing import Optional
|
|
2
|
+
|
|
3
|
+
from aiohttp import ClientSession
|
|
4
|
+
|
|
5
|
+
from torrent_tracker_search.common.TrackerResponse import TrackerResponse
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class TrackerClient:
|
|
9
|
+
|
|
10
|
+
session: Optional[ClientSession] = None
|
|
11
|
+
|
|
12
|
+
async def get(self, url: str, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse: ...
|
|
13
|
+
|
|
14
|
+
async def post_raw(self, url: str, body: dict, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse: ...
|
|
15
|
+
|
|
16
|
+
async def post_form_data(self, url: str, body: dict, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse: ...
|
|
17
|
+
|
|
18
|
+
async def post_form_data_encoded(self, url: str, body: dict, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse: ...
|
|
19
|
+
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
from dataclasses import dataclass
|
|
2
|
+
from typing import Dict
|
|
3
|
+
|
|
4
|
+
from multidict import CIMultiDict
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
@dataclass
|
|
8
|
+
class TrackerResponse:
|
|
9
|
+
headers: CIMultiDict[str]
|
|
10
|
+
status_code: int
|
|
11
|
+
body: bytes
|
|
12
|
+
|
|
13
|
+
@property
|
|
14
|
+
def cookies(self) -> Dict[str, str]:
|
|
15
|
+
cookies = {}
|
|
16
|
+
cookie_string = getattr(self.headers, "cookies", "")
|
|
17
|
+
if cookie_string == "":
|
|
18
|
+
return cookies
|
|
19
|
+
cookie_strings = cookie_string.split(";")
|
|
20
|
+
for cookie_string in cookie_strings:
|
|
21
|
+
cookie_name, cookie_value = cookie_string.split("=")
|
|
22
|
+
cookie_name = cookie_name.strip()
|
|
23
|
+
cookies[cookie_name] = cookie_value
|
|
24
|
+
return cookies
|
|
25
|
+
|
|
File without changes
|
|
File without changes
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
from typing import Final, Optional
|
|
2
|
+
|
|
3
|
+
from torrent_tracker_search.common.TrackerClient import TrackerClient
|
|
4
|
+
from torrent_tracker_search.common.TrackerRequestException import TrackerRequestException
|
|
5
|
+
from torrent_tracker_search.common.TrackerResponse import TrackerResponse
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class NNMClubClient(TrackerClient):
|
|
9
|
+
BASE_URL: Final[str] = "https://nnmclub.to/forum"
|
|
10
|
+
SESSION_COOKIE_KEY: Final[str] = "phpbb2mysql_4_sid"
|
|
11
|
+
|
|
12
|
+
async def get(self, url: str, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse:
|
|
13
|
+
async with self.session.get(url=url, params=params, ssl=False, allow_redirects=allow_redirects) as response:
|
|
14
|
+
success_status_code = 200 if allow_redirects else 302
|
|
15
|
+
if response.status != success_status_code:
|
|
16
|
+
raise TrackerRequestException()
|
|
17
|
+
else:
|
|
18
|
+
return TrackerResponse(
|
|
19
|
+
headers=response.headers.copy(),
|
|
20
|
+
status_code=response.status,
|
|
21
|
+
body=await response.content.read()
|
|
22
|
+
)
|
|
23
|
+
|
|
24
|
+
async def post_form_data_encoded(self, url: str, body: dict, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse:
|
|
25
|
+
async with self.session.post(url=url, data=body, ssl=False, allow_redirects=allow_redirects, params=params) as response:
|
|
26
|
+
success_status_code = 200 if allow_redirects else 302
|
|
27
|
+
if response.status == success_status_code:
|
|
28
|
+
return TrackerResponse(
|
|
29
|
+
headers=response.headers.copy(),
|
|
30
|
+
status_code=response.status,
|
|
31
|
+
body=await response.content.read()
|
|
32
|
+
)
|
|
33
|
+
else:
|
|
34
|
+
raise TrackerRequestException()
|
|
35
|
+
|
|
36
|
+
async def post_form_data(self, url: str, body: dict, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse:
|
|
37
|
+
async with self.session.post(url=url, data=body, ssl=False, allow_redirects=allow_redirects, params=params) as response:
|
|
38
|
+
success_status_code = 200 if allow_redirects else 302
|
|
39
|
+
if response.status == success_status_code:
|
|
40
|
+
return TrackerResponse(
|
|
41
|
+
headers=response.headers.copy(),
|
|
42
|
+
status_code=response.status,
|
|
43
|
+
body=await response.content.read()
|
|
44
|
+
)
|
|
45
|
+
else:
|
|
46
|
+
raise TrackerRequestException()
|
|
47
|
+
|
|
@@ -0,0 +1,72 @@
|
|
|
1
|
+
from typing import List, Optional
|
|
2
|
+
|
|
3
|
+
from torrent_tracker_search.common.TrackerClient import TrackerClient
|
|
4
|
+
from torrent_tracker_search.source.nnmclub.NNMClubClient import NNMClubClient
|
|
5
|
+
from torrent_tracker_search.source.nnmclub.NNMClubURL import NNMClubURL
|
|
6
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubSearchItem import NNMClubSearchItem
|
|
7
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubTorrentFile import NNMClubTorrentFile
|
|
8
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubTorrentItem import NNMClubTorrentItem
|
|
9
|
+
from torrent_tracker_search.source.nnmclub.parser.NNMClubBBCodeParser import NNMClubBBCodeParser
|
|
10
|
+
from torrent_tracker_search.source.nnmclub.parser.NNMClubSearchParser import NNMClubSearchParser
|
|
11
|
+
from torrent_tracker_search.source.nnmclub.parser.NNMClubTorrentFilesParser import NNMClubTorrentFilesParser
|
|
12
|
+
from torrent_tracker_search.source.nnmclub.parser.NNMClubTorrentParser import NNMClubTorrentParser
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
class NNMClubService:
|
|
16
|
+
|
|
17
|
+
def __init__(self, client: TrackerClient):
|
|
18
|
+
self._client: TrackerClient = client
|
|
19
|
+
|
|
20
|
+
async def search(self, query: str) -> List[NNMClubSearchItem]:
|
|
21
|
+
response = await self._client.get(
|
|
22
|
+
url=NNMClubURL.TRACKER.url,
|
|
23
|
+
params={
|
|
24
|
+
"nm": query,
|
|
25
|
+
"f": "-1",
|
|
26
|
+
"search_submit": ""
|
|
27
|
+
}
|
|
28
|
+
)
|
|
29
|
+
body = response.body.decode("Windows-1251")
|
|
30
|
+
return NNMClubSearchParser.parse(body)
|
|
31
|
+
|
|
32
|
+
def login(self, session_id: str):
|
|
33
|
+
self._client.session.cookie_jar.update_cookies({NNMClubClient.SESSION_COOKIE_KEY: session_id})
|
|
34
|
+
|
|
35
|
+
async def torrent_files(self, torrent_id: int) -> Optional[NNMClubTorrentFile]:
|
|
36
|
+
response = await self._client.get(
|
|
37
|
+
url=NNMClubURL.FILE_LIST.url,
|
|
38
|
+
params={
|
|
39
|
+
"attach_id": torrent_id
|
|
40
|
+
}
|
|
41
|
+
)
|
|
42
|
+
return NNMClubTorrentFilesParser.parse(response.body.decode("Windows-1251"))
|
|
43
|
+
|
|
44
|
+
async def torrent_bb_code(self, torrent_post_id: int) -> Optional[str]:
|
|
45
|
+
response = await self._client.get(
|
|
46
|
+
url=NNMClubURL.POSTING.url,
|
|
47
|
+
params={
|
|
48
|
+
"mode": "quote",
|
|
49
|
+
"p": torrent_post_id
|
|
50
|
+
}
|
|
51
|
+
)
|
|
52
|
+
return NNMClubBBCodeParser.parse(response.body.decode("Windows-1251"))
|
|
53
|
+
|
|
54
|
+
async def torrent(self, topic_id: int) -> Optional[NNMClubTorrentItem]:
|
|
55
|
+
response = await self._client.get(
|
|
56
|
+
url=NNMClubURL.VIEW_TOPIC.url,
|
|
57
|
+
params={
|
|
58
|
+
"t": topic_id
|
|
59
|
+
}
|
|
60
|
+
)
|
|
61
|
+
data = NNMClubTorrentParser.parse(response.body.decode("Windows-1251"))
|
|
62
|
+
if data is not None:
|
|
63
|
+
return NNMClubTorrentItem(
|
|
64
|
+
id=data["id"],
|
|
65
|
+
post_id=data["post_id"],
|
|
66
|
+
html_code=data["html_code"],
|
|
67
|
+
magnet_link=data["magnet_link"],
|
|
68
|
+
bb_code=await self.torrent_bb_code(torrent_post_id=data["post_id"]),
|
|
69
|
+
files=await self.torrent_files(torrent_id=data["id"])
|
|
70
|
+
)
|
|
71
|
+
else:
|
|
72
|
+
return None
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
from enum import Enum
|
|
2
|
+
|
|
3
|
+
from torrent_tracker_search.source.nnmclub.NNMClubClient import NNMClubClient
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
class NNMClubURL(Enum):
|
|
7
|
+
MAIN = "index.php"
|
|
8
|
+
TRACKER = "tracker.php"
|
|
9
|
+
POSTING = "posting.php"
|
|
10
|
+
VIEW_TOPIC = "viewtopic.php"
|
|
11
|
+
FILE_LIST = "filelst.php"
|
|
12
|
+
|
|
13
|
+
@property
|
|
14
|
+
def url(self) -> str:
|
|
15
|
+
return f"{NNMClubClient.BASE_URL}/{self.value}"
|
|
File without changes
|
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
from dataclasses import dataclass
|
|
2
|
+
from datetime import datetime
|
|
3
|
+
|
|
4
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubAuthorLink import NNMClubAuthorLink
|
|
5
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubForumLink import NNMClubForumLink
|
|
6
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubTopicLink import NNMClubTopicLink
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
@dataclass
|
|
10
|
+
class NNMClubSearchItem:
|
|
11
|
+
id: int # id for download torrent file
|
|
12
|
+
author: NNMClubAuthorLink
|
|
13
|
+
forum: NNMClubForumLink
|
|
14
|
+
topic: NNMClubTopicLink
|
|
15
|
+
size: int
|
|
16
|
+
seed_count: int
|
|
17
|
+
leech_count: int
|
|
18
|
+
added_at: datetime
|
torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/model/NNMClubTorrentItem.py
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
from dataclasses import dataclass
|
|
2
|
+
from typing import Optional, List
|
|
3
|
+
|
|
4
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubTorrentFile import NNMClubTorrentFile
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
@dataclass
|
|
8
|
+
class NNMClubTorrentItem:
|
|
9
|
+
id: int
|
|
10
|
+
post_id: int
|
|
11
|
+
html_code: str
|
|
12
|
+
magnet_link: str
|
|
13
|
+
bb_code: Optional[str] = None
|
|
14
|
+
files: Optional[List[NNMClubTorrentFile]] = None
|
|
File without changes
|
torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/NNMClubBBCodeParser.py
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
from typing import Optional
|
|
2
|
+
|
|
3
|
+
from bs4 import BeautifulSoup
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
class NNMClubBBCodeParser:
|
|
7
|
+
|
|
8
|
+
@classmethod
|
|
9
|
+
def parse(cls, html: str) -> Optional[str]:
|
|
10
|
+
soup = BeautifulSoup(html, "html.parser")
|
|
11
|
+
textarea = soup.find("textarea")
|
|
12
|
+
if textarea is not None:
|
|
13
|
+
return textarea.text
|
|
14
|
+
else:
|
|
15
|
+
return None
|
torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/NNMClubSearchParser.py
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
from datetime import datetime
|
|
2
|
+
from typing import List
|
|
3
|
+
|
|
4
|
+
from bs4 import BeautifulSoup, Tag
|
|
5
|
+
|
|
6
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubAuthorLink import NNMClubAuthorLink
|
|
7
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubForumLink import NNMClubForumLink
|
|
8
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubSearchItem import NNMClubSearchItem
|
|
9
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubTopicLink import NNMClubTopicLink
|
|
10
|
+
from torrent_tracker_search.source.nnmclub.parser import get_forum_id, get_user_id, get_torrent_id, get_topic_id
|
|
11
|
+
|
|
12
|
+
|
|
13
|
+
class NNMClubSearchParser:
|
|
14
|
+
|
|
15
|
+
@classmethod
|
|
16
|
+
def parse(cls, html: str) -> List[NNMClubSearchItem]:
|
|
17
|
+
soup = BeautifulSoup(html, "html.parser")
|
|
18
|
+
content_table = soup.find("table", attrs={"class": "forumline tablesorter"})
|
|
19
|
+
result = list()
|
|
20
|
+
for item_tr in content_table.tbody.childGenerator():
|
|
21
|
+
if type(item_tr) is Tag:
|
|
22
|
+
result.append(cls.parse_item(item_tr))
|
|
23
|
+
return result
|
|
24
|
+
|
|
25
|
+
@classmethod
|
|
26
|
+
def parse_item(cls, item_tr: Tag) -> NNMClubSearchItem:
|
|
27
|
+
items = [td for td in item_tr.find_all("td")]
|
|
28
|
+
if len(items) == 10:
|
|
29
|
+
_, forum_td, topic_td, author_td, torrent_td, size_td, seed_td, leech_td, reply_td, added_at_td = items
|
|
30
|
+
elif len(items) == 11:
|
|
31
|
+
_, forum_td, topic_td, author_td, torrent_td, size_td, _, seed_td, leech_td, reply_td, added_at_td = items
|
|
32
|
+
else:
|
|
33
|
+
raise Exception(f"Allowed only 10 items. Parser is broken. Now items count {len(items)}")
|
|
34
|
+
|
|
35
|
+
forum = NNMClubForumLink(
|
|
36
|
+
id=get_forum_id(forum_td),
|
|
37
|
+
name=str(forum_td.text).strip("\n")
|
|
38
|
+
)
|
|
39
|
+
author = NNMClubAuthorLink(
|
|
40
|
+
id=get_user_id(author_td),
|
|
41
|
+
name=str(author_td.text).strip("\n")
|
|
42
|
+
)
|
|
43
|
+
return NNMClubSearchItem(
|
|
44
|
+
id=get_torrent_id(torrent_td),
|
|
45
|
+
topic=NNMClubTopicLink(
|
|
46
|
+
id=get_topic_id(topic_td),
|
|
47
|
+
name=topic_td.a.text,
|
|
48
|
+
),
|
|
49
|
+
author=author,
|
|
50
|
+
forum=forum,
|
|
51
|
+
size=int(size_td.u.text),
|
|
52
|
+
seed_count=int(seed_td.text),
|
|
53
|
+
leech_count=int(leech_td.text),
|
|
54
|
+
added_at=datetime.fromtimestamp(int(added_at_td.u.text))
|
|
55
|
+
)
|
|
@@ -0,0 +1,96 @@
|
|
|
1
|
+
import os
|
|
2
|
+
from typing import List, Optional
|
|
3
|
+
|
|
4
|
+
from bs4 import BeautifulSoup, Tag
|
|
5
|
+
|
|
6
|
+
from torrent_tracker_search.source.nnmclub.model.NNMClubTorrentFile import NNMClubTorrentFile
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
class NNMClubTorrentFilesParser:
|
|
10
|
+
|
|
11
|
+
@classmethod
|
|
12
|
+
def parse(cls, html: str) -> Optional[NNMClubTorrentFile]:
|
|
13
|
+
soup = BeautifulSoup(html, "html.parser")
|
|
14
|
+
items: List[NNMClubTorrentFile] = []
|
|
15
|
+
content_table = soup.find("table")
|
|
16
|
+
if content_table is None:
|
|
17
|
+
return None
|
|
18
|
+
for item in content_table.tbody.childGenerator():
|
|
19
|
+
if type(item) is Tag:
|
|
20
|
+
cls.parse_item(item, items)
|
|
21
|
+
root_folder = items[0]
|
|
22
|
+
f = cls.reassemble_to_folders(items[1:])
|
|
23
|
+
root_folder.files = f.files
|
|
24
|
+
cls.calculate_folder_size(root_folder)
|
|
25
|
+
return root_folder
|
|
26
|
+
|
|
27
|
+
@classmethod
|
|
28
|
+
def calculate_folder_size(cls, folder: NNMClubTorrentFile):
|
|
29
|
+
"""Calculate the total size of the folder by summing up the sizes of contained files and subfolders."""
|
|
30
|
+
if not folder.is_folder:
|
|
31
|
+
return folder.size
|
|
32
|
+
|
|
33
|
+
total_size = 0
|
|
34
|
+
for file in folder.files:
|
|
35
|
+
if file.is_folder:
|
|
36
|
+
total_size += cls.calculate_folder_size(file)
|
|
37
|
+
else:
|
|
38
|
+
total_size += file.size
|
|
39
|
+
folder.size = total_size
|
|
40
|
+
return folder.size
|
|
41
|
+
|
|
42
|
+
@classmethod
|
|
43
|
+
def reassemble_to_folders(cls, file_list):
|
|
44
|
+
def add_file_to_folder(folder, path_parts, size):
|
|
45
|
+
if not path_parts:
|
|
46
|
+
return
|
|
47
|
+
|
|
48
|
+
current_part = path_parts[0]
|
|
49
|
+
remaining_parts = path_parts[1:]
|
|
50
|
+
folder_dict = {file.name: file for file in folder.files}
|
|
51
|
+
|
|
52
|
+
if current_part not in folder_dict:
|
|
53
|
+
# If this part of the path is not in the folder, add it
|
|
54
|
+
if remaining_parts:
|
|
55
|
+
# If there are remaining parts, it's a folder
|
|
56
|
+
new_folder = NNMClubTorrentFile(name=current_part, is_folder=True, files=[], size=0)
|
|
57
|
+
folder.files.append(new_folder)
|
|
58
|
+
add_file_to_folder(new_folder, remaining_parts, size)
|
|
59
|
+
else:
|
|
60
|
+
# If there are no remaining parts, it's a file
|
|
61
|
+
new_file = NNMClubTorrentFile(name=current_part, is_folder=False, size=size, files=[])
|
|
62
|
+
folder.files.append(new_file)
|
|
63
|
+
else:
|
|
64
|
+
# If the folder exists, continue adding the remaining path
|
|
65
|
+
add_file_to_folder(folder_dict[current_part], remaining_parts, size)
|
|
66
|
+
|
|
67
|
+
root_folder = NNMClubTorrentFile(name='root', is_folder=True, files=[], size=0)
|
|
68
|
+
|
|
69
|
+
for file in file_list:
|
|
70
|
+
path_parts = file.name.split(os.sep)
|
|
71
|
+
add_file_to_folder(root_folder, path_parts, file.size)
|
|
72
|
+
|
|
73
|
+
return root_folder
|
|
74
|
+
|
|
75
|
+
@classmethod
|
|
76
|
+
def parse_item(cls, tr_code: Tag, items: list):
|
|
77
|
+
number, name, size_in_bytes, size_in_bites = list(tr_code.childGenerator())
|
|
78
|
+
if number.text.strip() == "Папка":
|
|
79
|
+
items.append(
|
|
80
|
+
NNMClubTorrentFile(
|
|
81
|
+
name=name.text.strip(),
|
|
82
|
+
is_folder=True,
|
|
83
|
+
files=[],
|
|
84
|
+
size=0
|
|
85
|
+
)
|
|
86
|
+
)
|
|
87
|
+
else:
|
|
88
|
+
items.append(
|
|
89
|
+
NNMClubTorrentFile(
|
|
90
|
+
name=name.text.strip(),
|
|
91
|
+
is_folder=False,
|
|
92
|
+
files=[],
|
|
93
|
+
size=int(size_in_bites.text.replace(",", ""))
|
|
94
|
+
)
|
|
95
|
+
)
|
|
96
|
+
|
torrent_tracker_search-0.2.0/torrent_tracker_search/source/nnmclub/parser/NNMClubTorrentParser.py
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
from typing import Optional
|
|
2
|
+
|
|
3
|
+
from bs4 import BeautifulSoup, Tag
|
|
4
|
+
|
|
5
|
+
from torrent_tracker_search.source.nnmclub.parser import get_torrent_id
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class NNMClubTorrentParser:
|
|
9
|
+
|
|
10
|
+
@classmethod
|
|
11
|
+
def parse(cls, html: str) -> Optional[dict]:
|
|
12
|
+
soup = BeautifulSoup(html, "html.parser")
|
|
13
|
+
table = soup.find("th", string="Сообщение").find_parent("table")
|
|
14
|
+
tables = [tag for tag in table.childGenerator() if type(tag) is Tag]
|
|
15
|
+
content_table = [tag for tag in tables[1].childGenerator() if type(tag) is Tag][1].table
|
|
16
|
+
if content_table is not None:
|
|
17
|
+
items = [tag for tag in content_table.childGenerator() if type(tag) is Tag]
|
|
18
|
+
header, _, torrent_page, torrent_details, _ = items
|
|
19
|
+
magnet_link = torrent_details.find("a", attrs={"title": "Примагнититься"})
|
|
20
|
+
torrent_id_a = torrent_details.find("a", string="Скачать")
|
|
21
|
+
torrent_id = get_torrent_id(torrent_id_a.parent)
|
|
22
|
+
return {
|
|
23
|
+
"id": int(torrent_id),
|
|
24
|
+
"post_id": int(content_table["id"].replace("post_", "")),
|
|
25
|
+
"html_code": torrent_page,
|
|
26
|
+
"magnet_link": magnet_link["href"]
|
|
27
|
+
}
|
|
28
|
+
else:
|
|
29
|
+
return None
|
|
30
|
+
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
from urllib.parse import urlparse
|
|
2
|
+
|
|
3
|
+
from bs4 import Tag
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
def get_query_param(source: Tag, param_key: str) -> str:
|
|
7
|
+
source_href = source.a["href"]
|
|
8
|
+
query = urlparse(source_href).query.split("&")
|
|
9
|
+
for item in query:
|
|
10
|
+
if item.startswith(f"{param_key}="):
|
|
11
|
+
query_name, query_value = item.split("=")
|
|
12
|
+
return query_value
|
|
13
|
+
raise Exception(f"Error on get quert param from {source}")
|
|
14
|
+
|
|
15
|
+
def get_forum_id(forum_td: Tag) -> int:
|
|
16
|
+
return int(get_query_param(forum_td,"f"))
|
|
17
|
+
|
|
18
|
+
def get_user_id(author_td: Tag) -> int:
|
|
19
|
+
return int(get_query_param(author_td, "pid"))
|
|
20
|
+
|
|
21
|
+
def get_torrent_id(torrent_td: Tag) -> int:
|
|
22
|
+
return int(get_query_param(torrent_td, "id"))
|
|
23
|
+
|
|
24
|
+
def get_topic_id(topic_td: Tag) -> int:
|
|
25
|
+
return int(get_query_param(topic_td, "t"))
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
from typing import Final, Optional
|
|
2
|
+
|
|
3
|
+
from torrent_tracker_search.common.TrackerClient import TrackerClient
|
|
4
|
+
from torrent_tracker_search.common.TrackerRequestException import TrackerRequestException
|
|
5
|
+
from torrent_tracker_search.common.TrackerResponse import TrackerResponse
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class RuTrackerClient(TrackerClient):
|
|
9
|
+
BASE_URL: Final[str] = "https://rutracker.org/forum"
|
|
10
|
+
SESSION_COOKIE_KEY: Final[str] = "bb_session"
|
|
11
|
+
|
|
12
|
+
async def get(self, url: str, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse:
|
|
13
|
+
async with self.session.get(url=url, params=params, ssl=False, allow_redirects=allow_redirects) as response:
|
|
14
|
+
success_status_code = 200 if allow_redirects else 302
|
|
15
|
+
if response.status != success_status_code:
|
|
16
|
+
raise TrackerRequestException()
|
|
17
|
+
else:
|
|
18
|
+
return TrackerResponse(
|
|
19
|
+
headers=response.headers.copy(),
|
|
20
|
+
status_code=response.status,
|
|
21
|
+
body=await response.content.read()
|
|
22
|
+
)
|
|
23
|
+
|
|
24
|
+
async def post_form_data_encoded(self, url: str, body: dict, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse:
|
|
25
|
+
async with self.session.post(url=url, data=body, ssl=False, allow_redirects=allow_redirects, params=params) as response:
|
|
26
|
+
success_status_code = 200 if allow_redirects else 302
|
|
27
|
+
if response.status == success_status_code:
|
|
28
|
+
return TrackerResponse(
|
|
29
|
+
headers=response.headers.copy(),
|
|
30
|
+
status_code=response.status,
|
|
31
|
+
body=await response.content.read()
|
|
32
|
+
)
|
|
33
|
+
else:
|
|
34
|
+
raise TrackerRequestException()
|
|
35
|
+
|
|
36
|
+
async def post_form_data(self, url: str, body: dict, params: Optional[dict] = None, allow_redirects: bool = True) -> TrackerResponse:
|
|
37
|
+
async with self.session.post(url=url, data=body, ssl=False, allow_redirects=allow_redirects, params=params) as response:
|
|
38
|
+
success_status_code = 200 if allow_redirects else 302
|
|
39
|
+
if response.status == success_status_code:
|
|
40
|
+
return TrackerResponse(
|
|
41
|
+
headers=response.headers.copy(),
|
|
42
|
+
status_code=response.status,
|
|
43
|
+
body=await response.content.read()
|
|
44
|
+
)
|
|
45
|
+
else:
|
|
46
|
+
raise TrackerRequestException()
|
|
47
|
+
|
|
@@ -0,0 +1,98 @@
|
|
|
1
|
+
import base64
|
|
2
|
+
import json
|
|
3
|
+
from typing import Optional, List
|
|
4
|
+
|
|
5
|
+
from torrent_tracker_search.common.TrackerClient import TrackerClient
|
|
6
|
+
from torrent_tracker_search.source.rutracker.RuTrackerClient import RuTrackerClient
|
|
7
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerSearchItem import RuTrackerSearchItem
|
|
8
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerTorrentFile import RuTrackerTorrentFile
|
|
9
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerTorrentItem import RuTrackerTorrentItem
|
|
10
|
+
from torrent_tracker_search.source.rutracker.parser.RuTrackerSearchParser import RuTrackerSearchParser
|
|
11
|
+
from torrent_tracker_search.source.rutracker.RuTrackerURL import RuTrackerURL
|
|
12
|
+
from torrent_tracker_search.source.rutracker.parser.RuTrackerTorrentFilesParser import RuTrackerTorrentFilesParser
|
|
13
|
+
from torrent_tracker_search.source.rutracker.parser.RuTrackerTorrentParser import RuTrackerTorrentParser
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
class RuTrackerService:
|
|
17
|
+
|
|
18
|
+
def __init__(self, client: TrackerClient):
|
|
19
|
+
self._client: TrackerClient = client
|
|
20
|
+
|
|
21
|
+
async def search(self, query: str) -> List[RuTrackerSearchItem]:
|
|
22
|
+
response = await self._client.get(
|
|
23
|
+
url=RuTrackerURL.TRACKER.url,
|
|
24
|
+
params={
|
|
25
|
+
"nm": query
|
|
26
|
+
}
|
|
27
|
+
)
|
|
28
|
+
body = response.body.decode("Windows-1251")
|
|
29
|
+
return RuTrackerSearchParser.items(body)
|
|
30
|
+
|
|
31
|
+
async def torrent(self, torrent_id: int) -> Optional[RuTrackerTorrentItem]:
|
|
32
|
+
response = await self._client.get(
|
|
33
|
+
url=RuTrackerURL.VIEW_TOPIC.url,
|
|
34
|
+
params={
|
|
35
|
+
"t": torrent_id
|
|
36
|
+
}
|
|
37
|
+
)
|
|
38
|
+
body = response.body.decode("Windows-1251")
|
|
39
|
+
torrent_dict = RuTrackerTorrentParser.parse(body)
|
|
40
|
+
if torrent_dict is not None:
|
|
41
|
+
form_token = RuTrackerTorrentParser.form_token(body)
|
|
42
|
+
bb_code = await self.torrent_bb_code(post_id=torrent_dict["post_id"], form_token=form_token)
|
|
43
|
+
if bb_code is not None:
|
|
44
|
+
bb_code = base64.standard_b64encode(bb_code.encode()).decode()
|
|
45
|
+
return RuTrackerTorrentItem(
|
|
46
|
+
id=torrent_dict["torrent_id"],
|
|
47
|
+
post_id=torrent_dict["post_id"],
|
|
48
|
+
html_code=base64.standard_b64encode(torrent_dict["html_code"]).decode(),
|
|
49
|
+
magnet_link=torrent_dict["magnet_link"],
|
|
50
|
+
bb_code=bb_code,
|
|
51
|
+
files=await self.torrent_files(torrent_id=torrent_id)
|
|
52
|
+
)
|
|
53
|
+
|
|
54
|
+
async def torrent_files(self, torrent_id: int) -> List[RuTrackerTorrentFile]:
|
|
55
|
+
response = await self._client.post_form_data(
|
|
56
|
+
url=RuTrackerURL.VIEW_TORRENT.url,
|
|
57
|
+
body={
|
|
58
|
+
"t": torrent_id
|
|
59
|
+
}
|
|
60
|
+
)
|
|
61
|
+
body = response.body.decode("Windows-1251")
|
|
62
|
+
return RuTrackerTorrentFilesParser.items(body)
|
|
63
|
+
|
|
64
|
+
async def torrent_bb_code(self, post_id: int, form_token: str) -> Optional[str]:
|
|
65
|
+
response = await self._client.post_form_data(
|
|
66
|
+
url=RuTrackerURL.AJAX.url,
|
|
67
|
+
body={
|
|
68
|
+
"action": "view_post",
|
|
69
|
+
"post_id": post_id,
|
|
70
|
+
"mode": "text",
|
|
71
|
+
"form_token": form_token
|
|
72
|
+
}
|
|
73
|
+
)
|
|
74
|
+
body = response.body.decode()
|
|
75
|
+
body_json: dict = json.loads(body)
|
|
76
|
+
return body_json["post_text"]
|
|
77
|
+
|
|
78
|
+
async def login(self, login: str, password: str) -> Optional[str]:
|
|
79
|
+
response = await self._client.post_form_data_encoded(
|
|
80
|
+
url=RuTrackerURL.LOGIN.url,
|
|
81
|
+
body={
|
|
82
|
+
"login_username": login,
|
|
83
|
+
"login_password": password,
|
|
84
|
+
"login": ""
|
|
85
|
+
},
|
|
86
|
+
allow_redirects=False
|
|
87
|
+
)
|
|
88
|
+
new_cookies = response.headers.getall("Set-Cookie")
|
|
89
|
+
for new_cookie in new_cookies:
|
|
90
|
+
if new_cookie.startswith(RuTrackerClient.SESSION_COOKIE_KEY):
|
|
91
|
+
cookie_string = new_cookie.split(";")[0]
|
|
92
|
+
cookie_name, cookie_value = cookie_string.split("=")
|
|
93
|
+
self._client.session.cookie_jar.update_cookies({RuTrackerClient.SESSION_COOKIE_KEY: cookie_value})
|
|
94
|
+
return cookie_value
|
|
95
|
+
return None
|
|
96
|
+
|
|
97
|
+
|
|
98
|
+
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
from enum import Enum
|
|
2
|
+
|
|
3
|
+
from torrent_tracker_search.source.rutracker.RuTrackerClient import RuTrackerClient
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
class RuTrackerURL(Enum):
|
|
7
|
+
MAIN = "index.php"
|
|
8
|
+
LOGIN = "login.php"
|
|
9
|
+
TRACKER = "tracker.php"
|
|
10
|
+
VIEW_TOPIC = "viewtopic.php"
|
|
11
|
+
VIEW_TORRENT = "viewtorrent.php"
|
|
12
|
+
AJAX = "ajax.php"
|
|
13
|
+
|
|
14
|
+
@property
|
|
15
|
+
def url(self) -> str:
|
|
16
|
+
return f"{RuTrackerClient.BASE_URL}/{self.value}"
|
|
File without changes
|
torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/RuTrackerSearchItem.py
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
from dataclasses import dataclass
|
|
2
|
+
from datetime import datetime
|
|
3
|
+
from typing import List
|
|
4
|
+
|
|
5
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerAuthorLink import RuTrackerAuthorLink
|
|
6
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerForumLink import RuTrackerForumLink
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
@dataclass
|
|
10
|
+
class RuTrackerSearchItem:
|
|
11
|
+
id: int # id for download torrent file
|
|
12
|
+
is_verified: bool
|
|
13
|
+
name: str
|
|
14
|
+
author: RuTrackerAuthorLink
|
|
15
|
+
forum: RuTrackerForumLink
|
|
16
|
+
tags: List[str]
|
|
17
|
+
size: int
|
|
18
|
+
seed_count: int
|
|
19
|
+
leech_count: int
|
|
20
|
+
download_count: int
|
|
21
|
+
added_at: datetime
|
torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/model/RuTrackerTorrentItem.py
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
from dataclasses import dataclass
|
|
2
|
+
from typing import Optional, List
|
|
3
|
+
|
|
4
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerTorrentFile import RuTrackerTorrentFile
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
@dataclass
|
|
8
|
+
class RuTrackerTorrentItem:
|
|
9
|
+
id: int
|
|
10
|
+
post_id: int
|
|
11
|
+
html_code: str
|
|
12
|
+
magnet_link: str
|
|
13
|
+
bb_code: Optional[str] = None
|
|
14
|
+
files: Optional[List[RuTrackerTorrentFile]] = None
|
|
File without changes
|
torrent_tracker_search-0.2.0/torrent_tracker_search/source/rutracker/parser/RuTrackerSearchParser.py
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
from datetime import datetime
|
|
2
|
+
from typing import List
|
|
3
|
+
|
|
4
|
+
from bs4 import BeautifulSoup, Tag
|
|
5
|
+
|
|
6
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerAuthorLink import RuTrackerAuthorLink
|
|
7
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerForumLink import RuTrackerForumLink
|
|
8
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerSearchItem import RuTrackerSearchItem
|
|
9
|
+
from torrent_tracker_search.source.rutracker.parser import get_forum_id, get_user_id
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
class RuTrackerSearchParser:
|
|
13
|
+
|
|
14
|
+
@staticmethod
|
|
15
|
+
def items(html: str) -> List[RuTrackerSearchItem]:
|
|
16
|
+
soup = BeautifulSoup(html, "html.parser")
|
|
17
|
+
content_table = soup.find("table", attrs={"id": "tor-tbl"})
|
|
18
|
+
table_body = content_table.tbody
|
|
19
|
+
result = []
|
|
20
|
+
for item in table_body.childGenerator():
|
|
21
|
+
if type(item) is Tag:
|
|
22
|
+
result.append(RuTrackerSearchParser.item(item))
|
|
23
|
+
return result
|
|
24
|
+
|
|
25
|
+
@staticmethod
|
|
26
|
+
def item(item: Tag) -> RuTrackerSearchItem:
|
|
27
|
+
items = [td for td in item.find_all("td")]
|
|
28
|
+
if len(items) == 10:
|
|
29
|
+
id_td, is_verified_td, forum_td, torrent_td, author_td, size_td, seed_td, leech_td, download_td, added_at_td = items
|
|
30
|
+
forum = RuTrackerForumLink(
|
|
31
|
+
id=get_forum_id(forum_td),
|
|
32
|
+
name=str(forum_td.text).strip("\n")
|
|
33
|
+
)
|
|
34
|
+
author = RuTrackerAuthorLink(
|
|
35
|
+
id=get_user_id(author_td),
|
|
36
|
+
name=str(author_td.text).strip("\n")
|
|
37
|
+
)
|
|
38
|
+
torrent_div, tags_div = torrent_td.find_all("div")
|
|
39
|
+
return RuTrackerSearchItem(
|
|
40
|
+
id=int(id_td["id"]),
|
|
41
|
+
is_verified=is_verified_td.text == "√",
|
|
42
|
+
name=str(torrent_div.text).strip("\n"),
|
|
43
|
+
tags=[tag_span.text for tag_span in tags_div.childGenerator()],
|
|
44
|
+
forum=forum,
|
|
45
|
+
author=author,
|
|
46
|
+
size=int(size_td["data-ts_text"]),
|
|
47
|
+
seed_count=int(seed_td.text),
|
|
48
|
+
leech_count=int(leech_td.text),
|
|
49
|
+
download_count=int(download_td.text),
|
|
50
|
+
added_at=datetime.fromtimestamp(int(added_at_td["data-ts_text"]))
|
|
51
|
+
)
|
|
52
|
+
else:
|
|
53
|
+
raise Exception(f"Allowed only 10 items. Parser is broken. Now items count {len(items)}")
|
|
54
|
+
|
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
from typing import List
|
|
2
|
+
|
|
3
|
+
from bs4 import BeautifulSoup
|
|
4
|
+
|
|
5
|
+
from torrent_tracker_search.source.rutracker.model.RuTrackerTorrentFile import RuTrackerTorrentFile
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class RuTrackerTorrentFilesParser:
|
|
9
|
+
|
|
10
|
+
@staticmethod
|
|
11
|
+
def items(html: str) -> List[RuTrackerTorrentFile]:
|
|
12
|
+
soup = BeautifulSoup(html, "html.parser")
|
|
13
|
+
return RuTrackerTorrentFilesParser.parse_tree(soup.ul)
|
|
14
|
+
|
|
15
|
+
@staticmethod
|
|
16
|
+
def parse_tree(element):
|
|
17
|
+
# Здесь мы собираем информацию обо всех элементах
|
|
18
|
+
data = []
|
|
19
|
+
if element.name == 'li':
|
|
20
|
+
# sub_data = {}
|
|
21
|
+
div = element.find('div')
|
|
22
|
+
if div:
|
|
23
|
+
# Получаем название
|
|
24
|
+
name = div.find('b').text
|
|
25
|
+
# sub_data['name'] = name
|
|
26
|
+
# Получаем возможный идентификатор
|
|
27
|
+
size = div.find('i')
|
|
28
|
+
if size:
|
|
29
|
+
size = int(size.text)
|
|
30
|
+
else:
|
|
31
|
+
size = 0
|
|
32
|
+
|
|
33
|
+
data.append(RuTrackerTorrentFile(
|
|
34
|
+
name=name,
|
|
35
|
+
size=size,
|
|
36
|
+
files=[],
|
|
37
|
+
is_folder=False
|
|
38
|
+
))
|
|
39
|
+
|
|
40
|
+
# Обработка вложенного списка
|
|
41
|
+
nested_ul = element.find('ul')
|
|
42
|
+
if nested_ul:
|
|
43
|
+
nested_data = RuTrackerTorrentFilesParser.parse_tree(nested_ul)
|
|
44
|
+
if nested_data:
|
|
45
|
+
new_size = data[-1].size
|
|
46
|
+
for file in nested_data:
|
|
47
|
+
new_size += file.size
|
|
48
|
+
data[-1].is_folder = True
|
|
49
|
+
data[-1].size = new_size
|
|
50
|
+
data[-1].files = nested_data # Добавляем дочерние элементы
|
|
51
|
+
|
|
52
|
+
elif element.name == 'ul':
|
|
53
|
+
for li in element.find_all('li', recursive=False):
|
|
54
|
+
data.extend(RuTrackerTorrentFilesParser.parse_tree(li))
|
|
55
|
+
|
|
56
|
+
return data
|
|
57
|
+
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
import json
|
|
2
|
+
from typing import Optional
|
|
3
|
+
|
|
4
|
+
from bs4 import BeautifulSoup
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
class RuTrackerTorrentParser:
|
|
8
|
+
|
|
9
|
+
@staticmethod
|
|
10
|
+
def form_token(html: str) -> str:
|
|
11
|
+
form_token_start_index = html.index("form_token")
|
|
12
|
+
form_token_end_index = html[form_token_start_index:].index(",")
|
|
13
|
+
raw_form_token = html[form_token_start_index:form_token_start_index+form_token_end_index]
|
|
14
|
+
form_token = raw_form_token.strip().replace("form_token: ", "").replace("'", "")
|
|
15
|
+
return form_token
|
|
16
|
+
|
|
17
|
+
@staticmethod
|
|
18
|
+
def parse(html: str) -> Optional[dict]:
|
|
19
|
+
soup = BeautifulSoup(html, "html.parser")
|
|
20
|
+
torrent_html = soup.find("div", attrs={"class": "post_body"})
|
|
21
|
+
if torrent_html is not None:
|
|
22
|
+
props = json.loads(torrent_html["data-ext_link_data"])
|
|
23
|
+
post_id = int(props["p"])
|
|
24
|
+
torrent_id = int(props["t"])
|
|
25
|
+
magnet_link_a = soup.find("a", attrs={"data-topic_id": torrent_id})
|
|
26
|
+
magnet_link = magnet_link_a["href"]
|
|
27
|
+
return {
|
|
28
|
+
"post_id": post_id,
|
|
29
|
+
"torrent_id": torrent_id,
|
|
30
|
+
"magnet_link": magnet_link,
|
|
31
|
+
"html_code": torrent_html.encode()
|
|
32
|
+
}
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
from urllib.parse import urlparse
|
|
2
|
+
|
|
3
|
+
from bs4 import Tag
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
def get_forum_id(forum_td: Tag) -> int:
|
|
7
|
+
forum_href = forum_td.div.a["href"]
|
|
8
|
+
query = urlparse(forum_href).query.split("&")
|
|
9
|
+
for item in query:
|
|
10
|
+
if item.startswith("f="):
|
|
11
|
+
query_name, query_value = item.split("=")
|
|
12
|
+
return int(query_value)
|
|
13
|
+
raise Exception(f"Error on get forum id from {forum_href}")
|
|
14
|
+
|
|
15
|
+
def get_user_id(author_td: Tag) -> int:
|
|
16
|
+
author_href = author_td.div.a["href"]
|
|
17
|
+
query = urlparse(author_href).query.split("&")
|
|
18
|
+
for item in query:
|
|
19
|
+
if item.startswith("pid="):
|
|
20
|
+
query_name, query_value = item.split("=")
|
|
21
|
+
return int(query_value)
|
|
22
|
+
raise Exception(f"Error on get author id from {author_td}")
|
|
23
|
+
|