[750g] working, get_recipe OK

modules/750g/browser.py

@@ -28,11 +28,11 @@ __all__ = ['SevenFiftyGramsBrowser']
 class SevenFiftyGramsBrowser(BaseBrowser):
     DOMAIN = 'www.750g.com'
     PROTOCOL = 'http'
-    ENCODING = 'utf-8'
+    ENCODING = 'windows-1252'
     USER_AGENT = BaseBrowser.USER_AGENTS['wget']
     PAGES = {
         'http://www.750g.com/recettes_.*.htm': ResultsPage,
-        'http://www.750g.com/.*r[0-9]*.htm': RecipePage,
+        'http://www.750g.com/fiche_de_cuisine_complete.htm\?recettes_id=[0-9]*': RecipePage,
         }
 
     def iter_recipes(self, pattern):
@@ -41,6 +41,6 @@ class SevenFiftyGramsBrowser(BaseBrowser):
         return self.page.iter_recipes()
 
     def get_recipe(self, id):
-        self.location('http://www.750g.com/%s.htm' % id)
+        self.location('http://www.750g.com/fiche_de_cuisine_complete.htm?recettes_id=%s' % id)
         assert self.is_on_page(RecipePage)
         return self.page.get_recipe(id)

modules/750g/pages.py

@@ -35,7 +35,8 @@ class ResultsPage(BasePage):
             if len(links) > 0:
                 link = links[0]
                 title = unicode(link.text)
-                id = unicode(link.attrib.get('href','').strip('/').replace('.htm','htm'))
+                #id = unicode(link.attrib.get('href','').strip('/').replace('.htm','htm'))
+                id = unicode(self.parser.select(div,'div.carnet-add a',1).attrib.get('href','').split('=')[-1])
                 thumbnail_url = NotAvailable
                 short_description = NotAvailable
 
@@ -76,28 +77,49 @@ class RecipePage(BasePage):
         instructions = NotAvailable
         comments = []
 
-        title = unicode(self.parser.select(self.document.getroot(),'h1.m_title',1).text_content().strip())
+        title = unicode(self.parser.select(self.document.getroot(),'head > title',1).text.split(' - ')[1])
-        main = self.parser.select(self.document.getroot(),'div.m_content_recette_main',1)
+        main = self.parser.select(self.document.getroot(),'div.recette_description',1)
-        preparation_time = int(self.parser.select(main,'p.m_content_recette_info span.preptime',1).text_content())
+
-        cooking_time = int(self.parser.select(main,'p.m_content_recette_info span.cooktime',1).text_content())
+        rec_infos = self.parser.select(self.document.getroot(),'div.recette_infos div.infos_column strong')
-        ing_header_line = self.parser.select(main,'p.m_content_recette_ingredients span',1).text_content()
+        for info_title in rec_infos:
-        if '(pour' in ing_header_line and ')' in ing_header_line:
+            if u'Temps de préparation' in unicode(info_title.text):
-            nb_person = int(ing_header_line.split('pour ')[-1].split('personnes)')[0].split()[0])
+                if info_title.tail.strip() != '':
-        ingredients = self.parser.select(main,'p.m_content_recette_ingredients',1).text_content().strip().split('- ')
+                    preparation_time = int(info_title.tail.split()[0])
-        ingredients=ingredients[1:]
+                    if 'h' in info_title.tail:
-        rinstructions = self.parser.select(main,'div.m_content_recette_todo',1).text_content().strip()
+                        preparation_time = 60*preparation_time
-        instructions = u''
+            if 'Temps de cuisson' in info_title.text:
-        for line in rinstructions.split('\n'):
+                if info_title.tail.strip() != '':
-            instructions += '%s\n'%line.strip()
+                    cooking_time = int(info_title.tail.split()[0])
-        instructions = instructions.strip('\n')
+                    if 'h' in info_title.tail:
-        imgillu = self.parser.select(self.document.getroot(),'a.m_content_recette_illu img')
+                        cooking_time = 60*cooking_time
+            if 'Nombre de personnes' in info_title.text:
+                if info_title.tail.strip() != '':
+                    nb_person = int(info_title.tail)
+
+        ingredients = []
+        p_ing = self.parser.select(main,'div.data.top.left > div.content p')
+        for ing in p_ing:
+            ingtxt = unicode(ing.text_content().strip())
+            if ingtxt != '':
+                ingredients.append(ingtxt)
+
+        lines_instr = self.parser.select(main,'div.data.top.right div.content li')
+        if len(lines_instr) > 0:
+            instructions = u''
+            for line in lines_instr:
+                inst = ' '.join(line.text_content().strip().split())
+                instructions += '%s\n'% inst
+            instructions = instructions.strip('\n')
+
+        imgillu = self.parser.select(self.document.getroot(),'div.resume_recette_illustree img.photo')
         if len(imgillu) > 0:
             picture_url = unicode(imgillu[0].attrib.get('src',''))
-        for divcom in self.parser.select(self.document.getroot(),'div.m_commentaire_row'):
+
-            note = self.parser.select(divcom,'div.m_commentaire_note span',1).text.strip()
+        for divcom in self.parser.select(self.document.getroot(),'div.comment-outer'):
-            user = self.parser.select(divcom,'div.m_commentaire_content span',1).text.strip()
+            comtxt = unicode(' '.join(divcom.text_content().strip().split()))
-            content = self.parser.select(divcom,'div.m_commentaire_content p',1).text.strip()
+            if u'| Répondre' in comtxt:
-            comments.append(u'user: %s, note: %s, comment: %s'%(user,note,content))
+                comtxt = comtxt.strip('0123456789').replace(u' | Répondre','')
+            comments.append(comtxt)
 
         recipe = Recipe(id,title)
         recipe.preparation_time = preparation_time