[poringa] add support

docs/supportedsites.md

@@ -685,6 +685,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Galleries</td>
     <td></td>
 </tr>
+<tr>
+    <td>Poringa</td>
+    <td>http://www.poringa.net/</td>
+    <td>Post Images, User Profiles, Search</td>
+    <td></td>
+</tr>
 <tr>
     <td>Pornhub</td>
     <td>https://www.pornhub.com/</td>

gallery_dl/extractor/__init__.py

@@ -122,6 +122,7 @@
     "pixnet",
     "plurk",
     "poipiku",
+    "poringa",
     "pornhub",
     "pornpics",
     "pururin",

gallery_dl/extractor/poringa.py

@@ -0,0 +1,132 @@
+# -*- coding: utf-8 -*-
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+"""Extractors for http://www.poringa.net/"""
+
+from .common import Extractor, Message
+from .. import text, exception
+from ..cache import cache
+import itertools
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?poringa\.net"
+
+
+class PoringaExtractor(Extractor):
+    category = "poringa"
+    directory_fmt = ("{category}", "{user}", "{post_id}")
+    filename_fmt = "{post_id}_{title}_{filename}.{extension}"
+    archive_fmt = "{post_id}_{num}"
+    root = "http://www.poringa.net/"
+
+    def __init__(self, match):
+        Extractor.__init__(self, match)
+        self.item = match.group(1)
+        self.__cookies = True
+
+    def items(self):
+        for post_id in self.posts():
+            url = "{}posts/imagenes/{}".format(self.root, post_id)
+
+            try:
+                page = self.request(url).text
+            except exception.HttpError as exc:
+                self.log.warning(
+                    "Unable to fetch posts for '%s' (%s)", post_id, exc)
+                continue
+
+            title, pos = text.extract(
+                page, 'property="og:title" content="', '"')
+            pos = page.index('<div class="main-info', pos)
+            user, pos = text.extract(
+                page, 'href="http://www.poringa.net/', '"', pos)
+
+            if not user:
+                user = "poringa"
+
+            data = {
+                "post_id"     : post_id,
+                "title"        : text.unescape(title),
+                "user"         : text.unquote(user),
+                "_http_headers": {"Referer": url},
+            }
+
+            print(data)
+            yield Message.Directory, data
+            main_post, pos = text.extract(
+                page,
+                'property="dc:content" role="main">',
+                '</div>',
+            )
+            for url in text.extract_iter(
+                main_post,
+                '<img class="imagen" border="0" src="',
+                '"',
+            ):
+                yield Message.Url, url, text.nameext_from_url(url, data)
+
+    def posts(self):
+        return ()
+
+    def request(self, url, **kwargs):
+        if self.__cookies:
+            self.__cookies = False
+            self.cookies.update(_cookie_cache())
+
+        for _ in range(5):
+            response = Extractor.request(self, url, **kwargs)
+            if response.cookies:
+                _cookie_cache.update("", response.cookies)
+            if response.content.find(
+                    b"<title>Please wait a few moments</title>", 0, 600) < 0:
+                return response
+            self.sleep(5.0, "check")
+
+    def _pagination(self, url, params):
+        for params["p"] in itertools.count(1):
+            page = self.request(url, params=params).text
+
+            posts_ids = PoringaPostExtractor.pattern.findall(page)
+            posts_ids = list(dict.fromkeys(posts_ids))
+            yield from posts_ids
+
+            if len(posts_ids) < 19:
+                return
+
+
+class PoringaPostExtractor(PoringaExtractor):
+    """Extractor for posts on poringa.net"""
+    subcategory = "post"
+    pattern = BASE_PATTERN + r"\/posts\/imagenes\/(\d+)\/[a-zA-Z0-9_-]+\.html"
+    example = "http://www.poringa.net/posts/imagenes/12/TITLE.html"
+
+    def posts(self):
+        return (self.item,)
+
+
+class PoringaUserExtractor(PoringaExtractor):
+    subcategory = "user"
+    pattern = BASE_PATTERN + r"\/([a-zA-Z0-9_-]+)$"
+    example = "http://www.poringa.net/USER"
+
+    def posts(self):
+        url = "{}buscar/?q={}".format(self.root, self.item)
+        return self._pagination(url, {})
+
+
+class PoringaSearchExtractor(PoringaExtractor):
+    subcategory = "search"
+    pattern = BASE_PATTERN + r"/buscar/\?&?q=([^&#]+)"
+    example = "http://www.poringa.net/buscar/?q=QUERY"
+
+    def posts(self):
+        url = self.root + "buscar/?"
+        params = {"q": text.unquote(self.item)}
+        return self._pagination(url, params)
+
+
+@cache()
+def _cookie_cache():
+    return ()

test/results/poringa.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+from gallery_dl.extractor import poringa
+
+
+__tests__ = (
+{
+    "#url"     : "http://www.poringa.net/posts/imagenes/3051081/Turrita-alto-ojete.html",
+    "#category": ("", "poringa", "post"),
+    "#class"   : poringa.PoringaPostExtractor,
+    "#pattern" : r"http:\/\/www\.poringa\.net\/posts\/imagenes\/3051081\/[a-zA-Z0-9_-]+\.html",
+
+    "post_id": "3051081",
+    "title"   : "turrita alto ojete...",
+    "user"    : "vipower1top",
+},
+
+{
+    "#url"     : "http://www.poringa.net/posts/imagenes/3095554/Otra-culona-de-instagram.html",
+    "#category": ("", "poringa", "post"),
+    "#class"   : poringa.PoringaPostExtractor,
+    "#pattern" : r"http:\/\/www\.poringa\.net\/posts\/imagenes\/3095554\/[a-zA-Z0-9_-]+\.html",
+
+    "album_id": "3095554",
+    "title"   : "Otra culona de instagram",
+    "user"    : "Expectro007",
+},
+
+{
+    "#url"     : "http://www.poringa.net/Expectro007",
+    "#category": ("", "poringa", "user"),
+    "#class"   : poringa.PoringaUserExtractor,
+    "#pattern" : r"http:\/\/www\.poringa\.net\/Expectro007$",
+},
+
+{
+    "#url"     : "http://www.poringa.net/buscar/?&q=yuslopez",
+    "#category": ("", "poringa", "search"),
+    "#class"   : poringa.PoringaSearchExtractor,
+    "#pattern" : r"http:\/\/www\.poringa\.net\/buscar\/\?&?q=yuslopez",
+},
+
+)