Better plugin handling.

Author: cc-d

bin/resolveimg.py

@@ -61,7 +61,6 @@
 
 i = imageresolver.ImageResolver(**kw_options)
 i.register(imageresolver.FileExtensionResolver())
-i.register(imageresolver.PluginResolver())
 i.register(imageresolver.WebpageResolver(**kw_options))
 
 print i.resolve(url)

imageresolver/__init__.py

@@ -149,24 +149,6 @@ def resolve(self,url,**kwargs):
 
 		return None
 
-class PluginResolver(object):
-	def resolve(self,url,**kwargs):
-		plugins = {}
-		path = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'plugins')
-		sys.path.insert(0, path)
-		for plugin_file in os.listdir(path):
-			filename, extension = os.path.splitext(plugin_file)
-			if extension == '.py' and filename != '__init__':
-				mod = __import__(filename)
-				plugins[filename] = mod.Plugin()		
-		sys.path.pop(0)
-		
-		for plugin in plugins.values():
-			image = plugin.get_image(url)
-			if image:
-				return image
-		return None
-
 class WebpageResolver(object):
 	def __init__(self,**kwargs):
 		self.load_images = kwargs.get('load_images',True)
@@ -261,12 +243,35 @@ def _score(self,image):
 
 		return score
 
+        def plugin_resolve(self,url,soup,**kwargs):
+                plugins = {}
+                path = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'plugins')
+                sys.path.insert(0, path)
+                for plugin_file in os.listdir(path):
+                        filename, extension = os.path.splitext(plugin_file)
+                        if extension == '.py' and filename != '__init__':
+                                mod = __import__(filename)
+                                plugins[filename] = mod.Plugin()
+                sys.path.pop(0)
+
+                for plugin in plugins.values():
+                        image = plugin.get_image(url,soup)
+                        if image:
+                                return image
+                return None
+
+	
 	def resolve(self,url,**kwargs):
 		logger.debug('Resolving as a webpage ' + str(url))
-
 		ir = ImageResolver()
 		content = ir.fetch(url)
 		soup = BeautifulSoup(content,self.parser)
+
+		plugin_image = self.plugin_resolve(url,soup)
+
+		if plugin_image:
+			return plugin_image
+
 		images = soup.find_all('img')
 
 		candidates = []

imageresolver/plugins/flickr.py

@@ -5,14 +5,11 @@
 from bs4 import BeautifulSoup
 
 class Plugin:
-	def get_image(self, url, **kwargs):
+	def get_image(self, url, soup):
 		if re.search('http(s*):\/\/www.flickr.com\/photos\/([^\/]*)\/([^\/]*)\/(.*)', url):
 			logger = logging.getLogger('ImageResolver')
 			logger.debug('Resolving using plugin ' + str(os.path.basename(__file__)) + ' ' +  str(url))
-			r = requests.get(url)
-			if r.status_code == 200:
-				soup = BeautifulSoup(r.text)
-				tag = soup.find('img', {'class':'main-photo'})
-				if tag:
-					return 'https:' + tag['src']
+			tag = soup.find('img', {'class':'main-photo'})
+			if tag:
+				return 'https:' + tag['src']
 		return None

imageresolver/plugins/imgur.py

@@ -6,30 +6,24 @@
 import logging
 
 class Plugin:
-	def get_image(self, url, **kwargs):
+	def get_image(self, url, soup):
 		if re.search('http(s*):\/\/(i\.|m\.)*imgur.com\/(gallery\/){0,1}(.*)', url):
 			logger = logging.getLogger('ImageResolver')
 			logger.debug('Resolving using plugin ' + str(os.path.basename(__file__)) + ' ' +  str(url))
 			parsed = urlparse(url)
 
 			if parsed.path[1:8] == 'gallery':
 				logger.debug('Detected imgur gallery.')
-				r = requests.get(url)
-				if r.status_code == 200:
-					soup = BeautifulSoup(r.text)
-					tag = soup.find('div', {'id':'1','class':'album-image'})
-					image = re.findall('i\.imgur.com\/.*\.\w+', str(tag))
-					if len(image) >= 1:
-						return 'http://' + image[0]
+				tag = soup.find('div', {'id':'1','class':'album-image'})
+				image = re.findall('i\.imgur.com\/.*\.\w+', str(tag))
+				if len(image) >= 1:
+					return 'http://' + image[0]
 
 			elif parsed.path[0:3] == '/a/':
 				logger.debug('Detected imgur album.')
-				r = requests.get(url)
-				if r.status_code == 200:
-					soup = BeautifulSoup(r.text)
-					tag = soup.find('meta',{'name':'twitter:image0:src'})
-					if tag:
-						return tag['content']
+				tag = soup.find('meta',{'name':'twitter:image0:src'})
+				if tag:
+					return tag['content']
 
 			else:
 				parsed = urlparse(url)

imageresolver/plugins/instagram.py

@@ -1,18 +1,14 @@
 import re
 import os
-import requests
 import logging
 from bs4 import BeautifulSoup
 
 class Plugin:
-	def get_image(self, url, **kwargs):
+	def get_image(self, url, soup):
 		if re.search('http(s*):\/\/instagr(\.am|am\.com)\/p\/([^\/]+)', url):
 			logger = logging.getLogger('ImageResolver')
 			logger.debug('Resolving using plugin ' + str(os.path.basename(__file__)) + ' ' +  str(url))
-			r = requests.get(url)
-			if r.status_code == 200:
-				soup = BeautifulSoup(r.text)
-				tag = soup.find('meta',{'property':'og:image'})
-				if tag:
-					return tag['content']
+			tag = soup.find('meta',{'property':'og:image'})
+			if tag:
+				return tag['content']
 		return None

imageresolver/plugins/twitter.py

@@ -1,25 +1,21 @@
 import re
 import os
-import requests
 import logging
 from urlparse import urlparse
 from bs4 import BeautifulSoup
 
 class Plugin:
-	def get_image(self, url, **kwargs):
+	def get_image(self, url, soup):
 		if re.search('http(s*):\/\/(mobile\.|m\.)*twitter.com\/[a-zA-z0-9]*\/status\/\d+', url):
 			logger = logging.getLogger('ImageResolver')
 			logger.debug('Resolving using plugin ' + str(os.path.basename(__file__)) + ' ' +  str(url))
 			parsed = urlparse(url)
-			r = requests.get(url)
-			if r.status_code == 200:
-				soup = BeautifulSoup(r.text)
-				if parsed.netloc.split('.')[0] == 'mobile':
-					tag = soup.find('img',{'class':'CroppedPhoto-img u-block'})
-					if tag:
-						return tag['src']
-				
-				else:
-					tag = soup.find('meta',{'property':'og:image'})
-					if tag:
-						return tag['content']
+			if parsed.netloc.split('.')[0] == 'mobile':
+				tag = soup.find('img',{'class':'CroppedPhoto-img u-block'})
+				if tag:
+					return tag['src']
+			
+			else:
+				tag = soup.find('meta',{'property':'og:image'})
+				if tag:
+					return tag['content']