From 9ef5ea8fb6cae200fd8142a1b39f4658bc670fda Mon Sep 17 00:00:00 2001
From: DebaucheryLibrarian <moonloop.adult@protonmail.com>
Date: Thu, 23 Jul 2020 00:55:55 +0200
Subject: [PATCH] Added the awkward pagination to PornCZ scraper.

---
 assets/components/filters/filter-bar.vue |  4 ++--
 config/default.js                        |  1 +
 src/scrapers/porncz.js                   | 22 ++++++++++++++--------
 src/utils/http.js                        | 12 ++++++++++--
 src/utils/qu.js                          |  2 ++
 5 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/assets/components/filters/filter-bar.vue b/assets/components/filters/filter-bar.vue
index 9692b062..c46baaf6 100644
--- a/assets/components/filters/filter-bar.vue
+++ b/assets/components/filters/filter-bar.vue
@@ -253,11 +253,11 @@ export default {
 	}
 
 	.filters-filter:not(:last-child) .filter {
-		padding: 1rem .5rem;
+		padding: .5rem;
 	}
 
 	.filters-filter:last-child .filter {
-		padding: 1rem 0 1rem .5rem;
+		padding: .5rem 0 .5rem .5rem;
 	}
 }
 </style>
diff --git a/config/default.js b/config/default.js
index c343e340..b35b32e2 100644
--- a/config/default.js
+++ b/config/default.js
@@ -170,6 +170,7 @@ module.exports = {
 			'silverstonedvd',
 			'silviasaint',
 		],
+		'porncz',
 		'gangbangcreampie',
 		'gloryholesecrets',
 		'aziani',
diff --git a/src/scrapers/porncz.js b/src/scrapers/porncz.js
index 19025143..747a20d0 100644
--- a/src/scrapers/porncz.js
+++ b/src/scrapers/porncz.js
@@ -17,8 +17,6 @@ function scrapeAll(scenes, channel) {
 
 		release.poster = query.img('.product-item-image img', 'src', { origin: channel.url });
 
-		console.log(release);
-
 		return release;
 	});
 }
@@ -65,15 +63,23 @@ function scrapeProfile({ query }, entity) {
 	return profile;
 }
 
-async function fetchLatest(channel, _page = 1) {
-	const url = `${channel.url}/en/new-videos?option=date&do=sort`;
+async function fetchLatest(channel, page = 1) {
+	const url = page === 1 ? `${channel.url}/en/new-videos` : `${channel.url}/en/new-videos?do=next`;
 
-	// TODO: session
-	await http.head(url);
-	const res = await qu.getAll(url, '.product-item');
+	// pagination state is kept in session, and new each 'page' includes all previous pages
+	const session = http.session();
+	const headers = { 'X-Requested-With': 'XMLHttpRequest' };
+
+	for (let i = 0; i < page - 1; i += 1) {
+		await http.get(url, headers, { useSession: session }); // eslint-disable-line no-await-in-loop
+	}
+
+	const res = await http.get(url, headers, { useSession: session });
 
 	if (res.ok) {
-		return scrapeAll(res.items, channel);
+		const items = qu.extractAll(res.body.snippets?.['snippet--videoItems'] || res.body, '.product-item');
+
+		return scrapeAll(items.slice((page - 1) * 16), channel);
 	}
 
 	return res.status;
diff --git a/src/utils/http.js b/src/utils/http.js
index 71c0ebe9..e59b80fa 100644
--- a/src/utils/http.js
+++ b/src/utils/http.js
@@ -65,8 +65,8 @@ async function handler({
 	}
 
 	const res = ['POST', 'PUT', 'PATCH'].includes(method.toUpperCase())
-		? await bhttp[method.toLowerCase()](url, body, reqOptions)
-		: await bhttp[method.toLowerCase()](url, reqOptions);
+		? await (options.useSession || bhttp)[method.toLowerCase()](url, body, reqOptions)
+		: await (options.useSession || bhttp)[method.toLowerCase()](url, reqOptions);
 
 	if (options?.stream && options?.destination) {
 		await pipeline(res, ...(options?.transforms || []), options?.destination);
@@ -131,8 +131,16 @@ async function post(url, body, headers, options) {
 	});
 }
 
+function session(headers, options) {
+	return bhttp.session({
+		headers,
+		options,
+	});
+}
+
 module.exports = {
 	get,
 	post,
 	head,
+	session,
 };
diff --git a/src/utils/qu.js b/src/utils/qu.js
index d10cc652..847d2487 100644
--- a/src/utils/qu.js
+++ b/src/utils/qu.js
@@ -435,6 +435,8 @@ module.exports = {
 	formatDate,
 	get,
 	getAll,
+	fetch: get,
+	fetchAll: getAll,
 	context: init,
 	contextAll: initAll,
 	ed: extractDate,