video to iframes

mmdc_modules.py

@@ -20,7 +20,6 @@ def api_request(action, pagename): #get page: content, metadata, images, imageif
     return page_content
 
 def api_page(pageid, query):
-    print 'API query:', query
     if query == 'content':
         api_response = api_request('action=query&pageids={}&prop=revisions&rvprop=content', pageid)
         response = ((api_response.get('revisions'))[0])['*']
@@ -28,17 +27,21 @@ def api_page(pageid, query):
         response = api_request('action=query&pageids={}&prop=info', pageid)
     elif query == 'articleimgs':
         response = api_request('action=query&pageids={}&prop=images', pageid)
+    elif query == 'file':
+        response = api_request('action=query&titles=File:{}&prop=imageinfo&iiprop=url',pageid)
+        pprint.pprint( response )
     elif query == 'imageinfo':
         pagename = pageid # in imageinfo titles are used instead of id 
         response = api_request('action=query&titles=File:{}&prop=imageinfo&iiprop=url&iiurlwidth=500', pagename)  # iiurlwidht dermines with of thumbnail         
     return response
 
-def api_img_url(filename): # get full-size's image url
+def api_file_url(filename): # get full urls
-    '''get url of image'''
+    page_content_dict = api_page(filename, 'file')   
-   page_content_dict = api_page(filename, 'fullimage')   
     if 'imageinfo' in page_content_dict.keys():
-       thumburl = ((page_content_dict.get('imageinfo'))[0].get('thumburl'))
+        imgurl = ((page_content_dict.get('imageinfo'))[0].get('url'))
-       return thumburl
+        return imgurl
+    else:
+        return None
    
 def api_thumb_url(filename):
     '''get thumbnail url of image'''

mmdc_pages.py

@@ -6,7 +6,7 @@
 #####
 import xml.etree.ElementTree as ET
 import html5lib, urllib2, json, pprint, re
-from mmdc_modules import api_thumb_url, pandoc2html, img_fullurl
+from mmdc_modules import api_thumb_url, pandoc2html, img_fullurl, api_file_url
 #import mmdc_create_json import api_thumb_url
 json_allworks_file = open('allworks_mmdc.json', 'r') # save json 
 json_allworks = json.loads(json_allworks_file.read())
@@ -15,8 +15,8 @@ pages_path = 'web/work'
 #def generate_xml():
 gallery_exp=re.compile('<gallery>.*?</gallery>')
 file_exp=re.compile('File:(.*?)(?=File:|<\/gallery>)')
-#img_exp=re.compile('(^.*?\.(gif|jpg|jpeg|png))', re.I)
+img_exp=re.compile('(File:|Image:)((.*?)\.(gif|jpg|jpeg|png))(?=\||File:|Image:|<\/gallery>)', re.I)
-img_exp=re.compile('File:((.*?)\.(gif|jpg|jpeg|png))(?=\||File:|<\/gallery>)', re.I)
+video_exp=re.compile('\{\{(.*?)\|(.*?)\}\}')
 
 def replace_gallery(content):
     # from <gallery>.*</gallery> imgs, return list of img ET elements
@@ -24,37 +24,54 @@ def replace_gallery(content):
     gallery_imgs = []
     gallery_found = re.findall(gallery_exp, content)
     content = re.sub(gallery_exp,  '', content)
-    print 'gallery_found', gallery_found
     for gallery in gallery_found: # in case there is more than 1 <gallery>
-        print 'GALLERY', gallery
         allfiles =re.findall(img_exp, gallery)
-        print 'ALLFILES', allfiles
         for imgfile in allfiles:
-            imgfile = imgfile[0]
+            imgfile = imgfile[1]
-            imgsrc = api_thumb_url(imgfile) # search for original image
+            imgsrc = api_file_url(imgfile) # search for original image
-            print imgfile, imgsrc
             img_el = ET.Element('img', attrib={'src': imgsrc})
             gallery_imgs.append(img_el)
-#            print 'gallery img', imgfile, ET.tostring(img_el)
     return content, gallery_imgs
 
+def replace_video(content):
+    print '-- Replacing Videos --'
+    videos = []
+    videos_found = re.findall(video_exp, content)
+    for video in videos_found:
+        video_provider =  str(video[0])
+        video_hash = str(video[1])
+        video_src = None
+        print video_provider, type(video_provider)
+
+        if (video_provider.lower()) == 'youtube':            
+            video_src="https://www.youtube.com/embed/" + video_hash
+        elif (video_provider.lower()) == 'vimeo':            
+            video_src="https://player.vimeo.com/video/" + video_hash
+            print 'VIMEO'
+
+        if video_src:
+            iframe_el = ET.Element('iframe', attrib={'src':video_src,  'width':'600px', 'height':'450px'})
+
+            videos.append(iframe_el)
+    content = re.sub(video_exp,  '', content)
+    return content, videos
+    
 def create_workpage( allworks_dict, work_key): # replace text content in dict with html nodes, holding the content    
     for key in allworks_dict.keys():
         if key in ['Description', 'Extra']: 
             mw_content = allworks_dict[key]
             if re.search(gallery_exp, mw_content):
                 mw_content, gallery_imgs = replace_gallery(mw_content)
-                print gallery_imgs
+                allworks_dict['Images'] = gallery_imgs
-                print mw_content.encode('utf-8')            
+            elif re.search(video_exp, mw_content):
-
+                print '-- Searching for Video --'
-
+                mw_content, videos = replace_video(mw_content)
+                allworks_dict['Video'] = videos
+                print mw_content, videos
 
                 
             allworks_dict[key] = pandoc2html( mw_content if key in allworks_dict.keys() else '' ) # convert to HTML
- #           print 'allworks_dict[key]', key#, allworks_dict[key]
             work_htmltree = html5lib.parseFragment(allworks_dict[key], namespaceHTMLElements=False)
-#            replace_gallery(work_htmltree)
-            
 #            print work_htmltree
 #            print ET.tostring(work_htmltree)
 
@@ -80,7 +97,7 @@ def create_workpage( allworks_dict, work_key): # replace text content in dict wi
 #        print work_htmltree
         allworks_dict[key] = work_htmltree
         allworks_dict.pop('Thumbnail', None) #remove thumnail
-#    pprint.pprint(allworks_dict)
+    pprint.pprint(allworks_dict)