add support for archive.org (pyload#4151)

Author: GammaC0de

src/pyload/plugins/accounts/ArchiveOrg.py

@@ -0,0 +1,50 @@
+# -*- coding: utf-8 -*-
+
+import json
+
+from pyload.core.network.http.exceptions import BadHeader
+
+from ..base.account import BaseAccount
+
+
+class ArchiveOrg(BaseAccount):
+    __name__ = "ArchiveOrg"
+    __type__ = "account"
+    __version__ = "0.01"
+    __status__ = "testing"
+
+    __description__ = """Archive.org account plugin"""
+    __license__ = "GPLv3"
+    __authors__ = [("GammaC0de", "nitzo2001[AT]yahoo[DOT]com")]
+
+    LOGIN_URL = "https://archive.org/account/login"
+    LOGIN_CHECK_URL = "https://archive.org/account/index.php"
+
+    def grab_info(self, user, password, data):
+        return {'validuntil': None,
+                'trafficleft': None,
+                'premium': False}
+
+    def signin(self, user, password, data):
+        html = self.load(self.LOGIN_CHECK_URL)
+        if "<title>cannot find account</title>" not in html:
+            self.skip_login()
+
+        else:
+            self.load(self.LOGIN_URL)
+            try:
+                html = self.load(self.LOGIN_URL, post={
+                    "username": user,
+                    "password": password,
+                    "remember": "true",
+                    "referer": "https://archive.org/",
+                    "login": "true",
+                    "submit_by_js": "true"
+                })
+            except BadHeader as exc:
+                self.fail_login(str(exc))
+
+            else:
+                json_data = json.loads(html)
+                if json_data["status"] != "ok":
+                    self.fail_login()

src/pyload/plugins/decrypters/ArchiveOrgFolder.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from ..base.decrypter import BaseDecrypter
+
+
+class ArchiveOrgFolder(BaseDecrypter):
+    __name__ = "ArchiveOrgFolder"
+    __type__ = "decrypter"
+    __version__ = "0.01"
+    __status__ = "testing"
+
+    __pattern__ = r"https?://(?:www\.)?archive\.org/details/.+"
+    __config__ = [
+        ("enabled", "bool", "Activated", True),
+        ("use_premium", "bool", "Use premium account if available", True),
+        (
+            "folder_per_package",
+            "Default;Yes;No",
+            "Create folder for each package",
+            "Default",
+        ),
+    ]
+
+    __description__ = """Archive.org decrypter plugin"""
+    __license__ = "GPLv3"
+    __authors__ = [("GammaC0de", "nitzo2001[AT]yahoo[DOT]com")]
+
+    LINK_PATTERN = r'<div><a href="(https://archive\.org/download/.+?)"'
+
+    NAME_PATTERN = r'itemprop="name">(.+?)<'
+
+    OFFLINE_PATTERN = r"Item cannot be found."
+    TEMP_OFFLINE_PATTERN = r"^unmatchable$"
+
+    def decrypt(self, pyfile):
+        self.data = self.load(pyfile.url)
+
+        m = re.search(self.NAME_PATTERN, self.data)
+        if m is not None:
+            name = m.group(1)
+        else:
+            name = pyfile.package().name
+
+        links = re.findall(self.LINK_PATTERN, self.data)
+        self.packages = [(name, links, name)]

src/pyload/plugins/downloaders/ArchiveOrg.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+
+from ..base.simple_downloader import SimpleDownloader
+
+
+class ArchiveOrg(SimpleDownloader):
+    __name__ = "ArchiveOrg"
+    __type__ = "downloader"
+    __version__ = "0.01"
+    __status__ = "testing"
+
+    __pattern__ = r"https?://(?:www\.)?archive\.org/download/.+"
+    __config__ = [
+        ("enabled", "bool", "Activated", True),
+        ("use_premium", "bool", "Use premium account if available", True),
+        ("fallback", "bool", "Fallback to free download if premium fails", True),
+        ("chk_filesize", "bool", "Check file size", True),
+        ("max_wait", "int", "Reconnect if waiting time is greater than minutes", 10),
+    ]
+
+    __description__ = """Archive.org downloader plugin"""
+    __license__ = "GPLv3"
+    __authors__ = [("GammaC0de", "nitzo2001[AT]yahoo[DOT]com")]
+
+    def setup(self):
+        self.multi_dl = True
+        self.resume_download = True
+        self.chunk_limit = -1