From 0d5099dbe429146cebb33ba7e8aee6b03167b91f Mon Sep 17 00:00:00 2001
From: Ivan Kulikov <ivankulikov187@gmail.com>
Date: Mon, 9 Sep 2019 08:51:46 +0300
Subject: [PATCH] adapter_swiorgru: issues was fixed. (metadata parsing was
 added, adult check was added)

---
 fanficfare/adapters/adapter_swiorgru.py | 59 +++++++++++++++++++------
 1 file changed, 46 insertions(+), 13 deletions(-)

diff --git a/fanficfare/adapters/adapter_swiorgru.py b/fanficfare/adapters/adapter_swiorgru.py
index 83c6d3ec..ba81067d 100644
--- a/fanficfare/adapters/adapter_swiorgru.py
+++ b/fanficfare/adapters/adapter_swiorgru.py
@@ -39,11 +39,11 @@ class SwiOrgRuAdapter(BaseSiteAdapter):
         self._setURL('http://' + self.getSiteDomain() + '/mlp-fim/story/'+self.story.getMetadata('storyId'))
 
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','swi')
+        self.story.setMetadata('siteabbrev','swiorgru')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%b %d, %Y"
+        self.dateformat = "%Y.%m.%d"
 
 
     @staticmethod # must be @staticmethod, don't remove it.
@@ -72,29 +72,64 @@ class SwiOrgRuAdapter(BaseSiteAdapter):
         soup = self.make_soup(data)
 
         title = soup.find('h1')
+        for tag in title.findAll('sup'):
+            tag.extract()
 
-        self.story.setMetadata('title', stripHTML(title))
+        self.story.setMetadata('title', stripHTML(title.text))
         logger.debug("Title: (%s)"%self.story.getMetadata('title'))
 
-        author_title = soup.find('strong', text = re.compile("Автор: "))
+        author_title = soup.find('strong', text = re.compile(u"Автор: "))
         if author_title == None:
-            logger.info('author_title no found... exiting')
-            sys.exit()
+            raise exceptions.FailedToDownload("Error downloading page: %s! Missing required author_title element!" % url)
 
         author = author_title.next_sibling
 
         self.story.setMetadata('authorId', author.text) # Author's name is unique
         self.story.setMetadata('authorUrl','http://'+self.host + author['href'])
-        self.story.setMetadata('author',author.text)
+        self.story.setMetadata('author', author.text)
         logger.debug("Author: (%s)"%self.story.getMetadata('author'))
-        
-        chapters_header = soup.find('h2', text = re.compile("Главы:"))
+
+        date_pub = soup.find('em', text = re.compile(r'\d{4}.\d{2}.\d{2}'))
+        if not date_pub == None:
+            self.story.setMetadata('datePublished', makeDate(date_pub.text, self.dateformat))
+
+        rating_label = soup.find('strong', text = re.compile(u"рейтинг:"))
+        if not rating_label == None:
+            rating = rating_label.next_sibling.next_sibling
+            self.story.setMetadata('rating', stripHTML(rating))
+
+            if not self.is_adult or self.getConfig("is_adult"):
+                if "NC-18" in rating:
+                    raise exceptions.AdultCheckRequired(self.url)
+
+        characters = soup.findAll('img', src=re.compile(r"/mlp-fim/img/chars/\d+.png"))
+        logger.debug("numCharacters: (%s)"%str(len(characters)))
+
+        for x in range(0,len(characters)):
+            character=characters[x]
+            self.story.addToList('characters', character['title'])
+
+        if soup.find('font', color = r"green", text = u"завершен"):
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        categories_label = soup.find('strong', text = u"категории:")
+        if not categories_label == None:
+            categories_element = categories_label.next_sibling.next_sibling
+            categories = re.findall(r'"(.+?)"', categories_element.text)
+            for x in range(0, len(categories)):
+                category=categories[x]
+                self.story.addToList('category', category)
+
+        chapters_header = soup.find('h2', text = re.compile(u"Главы:"))
         if chapters_header==None:
-            logger.info('chapters_header no found... exiting')
-            sys.exit()
+            raise exceptions.FailedToDownload("Error downloading page: %s! Missing required chapters_header element!" % url)
 
         chapters_table = chapters_header.next_sibling.next_sibling
 
+        self.story.setMetadata('language','Russian')
+
         chapters=chapters_table.findAll('a', href=re.compile(r'/mlp-fim/story/'+self.story.getMetadata('storyId')+"/chapter\d+"))
         self.story.setMetadata('numChapters', len(chapters))
         logger.debug("numChapters: (%s)"%str(self.story.getMetadata('numChapters')))
@@ -104,8 +139,6 @@ class SwiOrgRuAdapter(BaseSiteAdapter):
                 churl='http://'+self.host+chapter['href']
                 self.add_chapter(chapter,churl)
 
-        self.story.setMetadata('language','Russian')
-
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)