Merge pull request #106 from cryzed/master

Added adapter for quotev.com - thanks cryzed!

calibre-plugin/plugin-defaults.ini

@@ -1938,6 +1938,13 @@ extracategories:Psych
 ## Site dedicated to these categories/characters/ships
 extracategories:Queer as Folk
 
+[quotev.com]
+extra_valid_entries:pages,readers,reads,favorites
+pages_label:Pages
+readers_label:Readers
+reads_label:Reads
+favorites_label:Favorites
+
 [www.restrictedsection.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In

fanficfare/adapters/__init__.py

@@ -140,6 +140,7 @@ import adapter_forumssufficientvelocitycom
 import adapter_questionablequestingcom
 import adapter_ninelivesdarksolaceorg
 import adapter_masseffect2in
+import adapter_quotevcom
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need

fanficfare/adapters/adapter_quotevcom.py

@@ -0,0 +1,108 @@
+import re
+import urlparse
+import urllib2
+import datetime
+
+from .. import exceptions
+from base_adapter import BaseSiteAdapter
+
+SITE_DOMAIN = 'quotev.com'
+STORY_URL_TEMPLATE = 'http://www.quotev.com/story/%s'
+
+
+def getClass():
+    return QuotevComAdapter
+
+
+def get_url_path_segments(url):
+    return tuple(filter(None, url.split('/')[3:]))
+
+
+class QuotevComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        story_id = get_url_path_segments(url)[1]
+        self._setURL(STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('storyId', story_id)
+        self.story.setMetadata('siteabbrev', SITE_DOMAIN)
+
+    @staticmethod
+    def getSiteDomain():
+        return SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return STORY_URL_TEMPLATE % '1234'
+
+    def getSiteURLPattern(self):
+        pattern = re.escape(STORY_URL_TEMPLATE.rsplit('%', 1)[0]) + r'(.+?)($|&|/)'
+        pattern = pattern.replace(r'http\:', r'https?\:')
+        pattern = pattern.replace(r'https?\:\/\/www\.', r'https?\:\/\/(www\.)?')
+        return pattern
+
+    def use_pagecache(self):
+        return True
+
+    def extractChapterUrlsAndMetadata(self):
+        try:
+            data = self._fetchUrl(self.url)
+        except urllib2.HTTPError:
+            raise exceptions.FailedToDownload(self.url)
+
+        soup = self.make_soup(data)
+
+        element = soup.find('div', {'class': 'result_head'})
+        if not element:
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        self.story.setMetadata('title', element.find('span', recursive=False).get_text())
+
+        element = soup.find('div', {'class': 'desc_creator'})('a')[1]
+        self.story.setMetadata('author', element.get_text())
+        self.story.setMetadata('authorId', get_url_path_segments(element['href'])[0])
+        self.story.setMetadata('authorUrl', urlparse.urljoin(self.url, element['href']))
+        self.setDescription(self.url, soup.find('div', id='qdesct'))
+        self.setCoverImage(self.url, urlparse.urljoin(self.url, soup.find('img', {'class': 'logo'})['src']))
+
+        for a in soup.find('div', {'class': 'tag'})('a'):
+            if a['href'] == '#':
+                continue
+
+            self.story.addToList('category', a.get_text())
+
+        elements = soup('span', {'class': 'q_time'})
+        self.story.setMetadata('datePublished', datetime.datetime.fromtimestamp(float(elements[0]['ts'])))
+        self.story.setMetadata('dateUpdated', datetime.datetime.fromtimestamp(float(elements[1]['ts'])))
+
+        for a in soup.find('div', id='rselect')('a'):
+            self.chapterUrls.append((a.get_text(), urlparse.urljoin(self.url, a['href'])))
+
+        self.story.setMetadata('numChapters', len(self.chapterUrls))
+
+        element = soup.find('div', {'class': 't'})('div', recursive=False)[1].div
+        data = filter(None, (x.strip() for x in element('span')[1].next_sibling.split(u'\xb7')))
+
+        if 'completed' in data:
+            self.story.setMetadata('status', 'Completed')
+            data.remove('completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        for datum in data:
+            value, key = datum.split()
+            self.story.setMetadata(key, value.replace(',', '').replace('.', ''))
+
+        self.story.setMetadata('favorites', soup.find('div', id='favqn').get_text())
+        self.story.setMetadata('comments', soup.find('a', id='comment_btn').span.get_text())
+
+    def getChapterText(self, url):
+        data = self._fetchUrl(url)
+        soup = self.make_soup(data)
+
+        element = soup.find('div', id='restxt')
+        for a in element('a'):
+            a.unwrap()
+
+        return self.utf8FromSoup(url, element)

fanficfare/defaults.ini

@@ -1918,6 +1918,13 @@ extracategories:Psych
 ## Site dedicated to these categories/characters/ships
 extracategories:Queer as Folk
 
+[quotev.com]
+extra_valid_entries:pages,readers,reads,favorites
+pages_label:Pages
+readers_label:Readers
+reads_label:Reads
+favorites_label:Favorites
+
 [www.restrictedsection.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In