Update chrysanthemumgarden.py

sources/en/c/chrysanthemumgarden.py

@@ -2,6 +2,7 @@
 import logging
 
 from lncrawl.core.crawler import Crawler
+from urllib.parse import urlparse
 
 logger = logging.getLogger(__name__)
 
@@ -17,11 +18,28 @@ def read_novel_info(self):
 
         possible_title = soup.select_one("h1.novel-title")
         assert possible_title, "No novel title"
+        raw_title = possible_title.select_one("span")
+        if raw_title:
+            raw_title.extract()
         self.novel_title = possible_title.text
         logger.info("Novel title: %s", self.novel_title)
 
-        # self.novel_author = soup.select_one('.bookinfo .status').text
-        # logger.info('%s', self.novel_author)
+        novel_info = soup.select_one(".novel-info")
+        for e in novel_info:
+            if e.text.strip().startswith("Author: "):
+                self.novel_author = e.replace("Author: ", "").strip()
+                logger.info("Novel author: %s", self.novel_author)
+                break
+
+        # possible_synopsis = soup.select_one(".entry-content")
+        # if possible_synopsis:
+        #     self.novel_synopsis = self.cleaner.extract_contents(possible_synopsis)
+        # logger.info("Novel synopsis: %s", self.novel_synopsis)
+
+        self.novel_tags = [
+            a.text.split(" (")[0].strip() for a in soup.select("a.series-tag")
+        ]
+        logger.info("Novel tags: %s", self.novel_tags)
 
         possible_image = soup.select_one(".novel-cover img")
         if possible_image:
@@ -44,8 +62,24 @@ def read_novel_info(self):
 
         self.volumes = [{"id": x, "title": ""} for x in volumes]
 
+    def login(self, email, password):
+        self.password = password
+
     def download_chapter_body(self, chapter):
-        soup = self.get_soup(chapter["url"])
+
+        chapter_url = chapter["url"]
+        soup = self.get_soup(chapter_url)
+
+        if soup.select_one("#site-pass"):
+            payload = {
+                "site-pass": self.password,
+                "nonce-site-pass": soup.select_one("#nonce-site-pass")["value"],
+                "_wp_http_referer": urlparse(chapter_url).path,
+            }
+
+            soup = self.make_soup(
+                self.submit_form(url=self.absolute_url(chapter_url), data=payload, multipart=True),
+            )
 
         bads = ["chrysanthemumgarden (dot) com", "Chrysanthemum Garden"]
 
@@ -59,7 +93,10 @@ def download_chapter_body(self, chapter):
 
             text = ""
             for span in p.select("span.jum"):
-                text += self.descramble_text(span.text) + " "
+                try:
+                    text += self.descramble_text(span.text) + " "
+                except IndexError:
+                    pass
 
             if not text:
                 text = p.text.strip()