Merge pull request #2277 from kuwoyuki/reaperscans

fix: reaperscans

lncrawl/core/scraper.py

@@ -223,9 +223,11 @@ def submit_form(
         headers = CaseInsensitiveDict(headers)
         headers.setdefault(
             "Content-Type",
-            "multipart/form-data"
-            if multipart
-            else "application/x-www-form-urlencoded; charset=UTF-8",
+            (
+                "multipart/form-data"
+                if multipart
+                else "application/x-www-form-urlencoded; charset=UTF-8"
+            ),
         )
         return self.post_response(url, data=data, headers=headers, **kwargs)
 
@@ -269,15 +271,15 @@ def get_json(self, url, headers={}, **kwargs) -> Any:
         response = self.get_response(url, headers=headers, **kwargs)
         return response.json()
 
-    def post_json(self, url, data={}, headers={}) -> Any:
+    def post_json(self, url, data={}, headers={}, **kwargs) -> Any:
         """Make a POST request and return the content as JSON object"""
         headers = CaseInsensitiveDict(headers)
         headers.setdefault("Content-Type", "application/json")
         headers.setdefault(
             "Accept",
             "application/json,text/plain,*/*",
         )
-        response = self.post_response(url, data=data, headers=headers)
+        response = self.post_response(url, data=data, headers=headers, **kwargs)
         return response.json()
 
     def submit_form_json(

sources/en/r/reaperscans.py

@@ -1,11 +1,11 @@
 # -*- coding: utf-8 -*-
+import json
 import logging
 from bs4 import Tag
 
 from lncrawl.core.crawler import Crawler
 
 logger = logging.getLogger(__name__)
-search_url = "https://reaperscans.com/?s=%s&post_type=wp-manga"
 
 
 class Reaperscans(Crawler):
@@ -22,72 +22,91 @@ def initialize(self):
                 "https://discord.gg/MaRegMFhRb",
                 "https://discord.gg/reapercomics",
                 "h ttps://discord.gg/reapercomic",
+                "https://discord.gg/sb2jqkv",
                 "____",
-                "Join our Discord for updates on releases!",
+                "Join our Discord",
             ]
         )
+        self.init_executor(ratelimit=0.9)
 
-    def search_novel(self, query):
-        query = query.lower().replace(" ", "+")
-        soup = self.get_soup(search_url % query)
-
-        results = []
-        for tab in soup.select(".c-tabs-item__content"):
-            a = tab.select_one(".post-title h3 a")
-            latest = tab.select_one(".latest-chap .chapter a").text
-            votes = tab.select_one(".rating .total_votes").text
-            results.append(
-                {
-                    "title": a.text.strip(),
-                    "url": self.absolute_url(a["href"]),
-                    "info": "%s | Rating: %s" % (latest, votes),
-                }
-            )
-
-        return results
+    def get_chapters_from_page(self, page, body):
+        url = self.absolute_url("/livewire/message/" + body["fingerprint"]["name"])
+        body["updates"] = [
+            {
+                "type": "callMethod",
+                "payload": {
+                    "id": "00000",
+                    "method": "gotoPage",
+                    "params": [page, "page"],
+                },
+            }
+        ]
+
+        response = self.post_json(url=url, data=json.dumps(body), timeout=10)
+        return self.make_soup(response["effects"]["html"])
+
+    def get_chapters_from_doc(self, dom):
+        return [
+            {
+                "title": a.select_one("p").text.strip(),
+                "url": self.absolute_url(a["href"]),
+            }
+            for a in dom.select("div[wire\\3A id] ul[role] li a")
+        ]
+
+    def insert_chapters(self, chapters):
+        self.chapters = [
+            {
+                "id": i + 1,
+                "title": x["title"],
+                "url": x["url"],
+            }
+            for i, x in enumerate(reversed(chapters))
+        ]
 
     def read_novel_info(self):
         logger.debug("Visiting %s", self.novel_url)
         soup = self.get_soup(self.novel_url)
 
-        possible_title = soup.select_one(".post-title h1")
-        assert isinstance(possible_title, Tag)
-        for span in possible_title.select("span"):
-            span.extract()
-        self.novel_title = possible_title.text.strip()
+        self.novel_title = soup.select_one("h1").text.strip()
         logger.info("Novel title: %s", self.novel_title)
 
-        possible_image = soup.select_one(".summary_image a img")
+        possible_image = soup.select_one(".h-full .w-full img")
         if isinstance(possible_image, Tag):
-            self.novel_cover = self.absolute_url(possible_image["data-src"])
+            self.novel_cover = self.absolute_url(possible_image["src"])
         logger.info("Novel cover: %s", self.novel_cover)
 
-        self.novel_author = " ".join(
-            [a.text.strip() for a in soup.select('.author-content a[href*="author"]')]
+        # livewire container
+        container = soup.select_one("main div[wire\\:id][wire\\:initial-data]")
+        # first page ssr json
+        body = json.loads(container["wire:initial-data"])
+        body.pop("effects")
+        # initial chapters from soup
+        chapters = self.get_chapters_from_doc(container)
+        page_count = 1
+        last_page = container.select_one(
+            'span[wire\\:key^="paginator-page"]:nth-last-child(2)'
         )
-        logger.info("%s", self.novel_author)
-
-        chapter_list_url = self.absolute_url("ajax/chapters", self.novel_url)
-        soup = self.post_soup(chapter_list_url, headers={"accept": "*/*"})
-        for a in reversed(
-            soup.select('.wp-manga-chapter:not(.premium-block) a[href*="/chapter"]')
-        ):  # This stops it from trying to download locked premium chapters.
-            for span in a.findAll("span"):  # Removes time and date from chapter title.
-                span.extract()
-            chap_id = len(self.chapters) + 1
-            vol_id = 1 + len(self.chapters) // 100
-            if chap_id % 100 == 1:
-                self.volumes.append({"id": vol_id})
-            self.chapters.append(
-                {
-                    "id": chap_id,
-                    "volume": vol_id,
-                    "title": a.text.strip(),
-                    "url": self.absolute_url(a["href"]),
-                }
-            )
+
+        if isinstance(last_page, Tag):
+            page_count = int(last_page.text.strip())
+        else:
+            self.insert_chapters(chapters)
+            # if we don't have the pagination el
+            return
+
+        toc_futures = [
+            self.executor.submit(self.get_chapters_from_page, k, body)
+            for k in range(2, page_count + 1)
+        ]
+        self.resolve_futures(toc_futures, desc="TOC", unit="page")
+        for f in toc_futures:
+            chapters.extend(self.get_chapters_from_doc(f.result()))
+
+        self.insert_chapters(chapters)
 
     def download_chapter_body(self, chapter):
-        soup = self.get_soup(chapter["url"])
-        contents = soup.select_one("div.text-left")
+        # TODO: better retry/timeout settings
+        soup = self.get_soup(chapter["url"], retry=3, timeout=10)
+        contents = soup.select_one("article")
         return self.cleaner.extract_contents(contents)