acastro
/
pzimediadesign
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

video and gallary parsing running

Browse Source
master
Castro0o 9 years ago
parent 2caa4afccf
commit 03a6f86144
2 changed files with 20 additions and 73 deletions
Show Stats Download Patch File Download Diff File

63
mmdc_modules.py
Unescape Escape View File

@ -150,68 +150,27 @@ def pandoc(filename, title, creator, date, website, thumbnail, bio, description,
def img_fullurl(parent):
imgs = parent.findall('.//img')
print 'len IMG', len(imgs)
for img in imgs:
src = img.get('src')
fullurl = api_thumb_url(src)
print '----- IMG', ET.tostring(img ), src, fullurl
if fullurl != None:
img.set('src', fullurl)
# fileurl = api_request(src, endpoint)# find url of file
gallery_exp=re.compile('<gallery>.*?</gallery>', re.S)
imgfile_exp=re.compile('(File:(.*?\.(gif|jpg|jpeg|png)))')# (?=File:|<\/gallery>)')
img_exp=re.compile('(File:|Image:)((.*?)\.(gif|jpg|jpeg|png))(?=\||File:|Image:|<\/gallery>)', re.I)
video_exp=re.compile('\{\{(.*?)\|(.*?)\}\}')
def replace_gallery(content):
gallery_imgs = []
gallery_found = re.findall(gallery_exp, content)
for gallery in gallery_found: # in case there is more than 1 <gallery>
allfiles =re.findall(imgfile_exp, gallery)
print 'ALLFILES', allfiles
for imgfile in allfiles:
imgfile = imgfile[1]
#imgsrc = imgfile
imgsrc = api_file_url(imgfile) # seaarch for original image
newimg = ''
gallery_imgs.append(imgsrc)
print 'GALLERY_IMGS', gallery_imgs
ungallery_imgs = " ".join(gallery_imgs)
print 'ungallery_imgs', ungallery_imgs
content = re.sub(gallery_exp, ungallery_imgs, content)
print 'images content', content
## BUG: Images are being replaced as <a>
# EG: <a class="uri" href="File:Mb-WordNet-tour-version2-08.png">File:Mb-WordNet-tour-version2-08.png</a> <a class="uri" href="File:Labanotation1.jpg">File:Labanotation1.jpg</a>
gallery_exp=re.compile('<gallery>(.*?)</gallery>', re.S)
imgfile_exp=re.compile('(File:(.*?)\.(gif|jpg|jpeg|png))')
def replace_gallery(content):
content = re.sub(imgfile_exp, '[[\g<1>]]', content) #add [[ ]] to File:.*?
content = re.sub(gallery_exp, '\g<1>', content) #remove gallery wrapper
return content
video_exp=re.compile('\{\{(.*?)\|(.*?)\}\}')
vimeo_exp=re.compile('\{\{vimeo\|(.*?)\}\}')
youtube_exp=re.compile('\{\{youtube\|(.*?)\}\}')
def replace_video(content):
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
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
if video_src:
videos.append(video_src)
iframe = "<iframe src='{}' width='600px' height='450px'> </iframe>".format(video_src)
content = re.sub(video_exp, iframe, content)
else:
content = re.sub(video_exp, '', content)
content = re.sub(vimeo_exp,"<iframe src='https://player.vimeo.com/video/\g<1>' width='600px' height='450px'> </iframe>", content)
content = re.sub(youtube_exp, "<iframe src='https://www.youtube.com/embed/\g<1>' width='600px' height='450px'> </iframe>", content)
return content
## Video Replacement: problem with video: iframe is placed inside <p> . It shouldn't
## replace gallery - not yet there

30
prototype_page.py
Unescape Escape View File

@ -20,48 +20,36 @@ from mmdc_modules import api_request, api_page, api_thumb_url, pandoc2html, pars
template = open("web/page-template.html", "r")
template = template.read()
# download
# download mw work page
pageid='15965'#Qq #'16025' #'15986'Jozeph #'16025'Mina
work = 'Q' #'Mina'#'User:Joak/graduation/catalog1'
workpage_mw = api_page(pageid, 'content')
print '------------------- workpage_mw'
if re.search(gallery_exp, workpage_mw):
print 'FOUND GALLERY'
workpage_mw = replace_gallery(workpage_mw)
if re.search(video_exp, workpage_mw):
workpage_mw = replace_video(workpage_mw)
print 'FOUND VIDEO'
'''
# parsing workpage_mw
workdict = parse_work(work, workpage_mw)
# parse workpage_mw
workpage_mw = replace_gallery(workpage_mw)
workpage_mw = replace_video(workpage_mw)
workdict = parse_work(work, workpage_mw) # create dictionary workpage_mw template
for key in workdict.keys():
if key in ['Extra', 'Description', 'Bio']:
workdict[key] = pandoc2html(workdict[key].encode('utf-8'))
# fill template with dictionary/mw_page values
workpage_html = template.format(title=workdict['Title'], creator=workdict['Creator'], date=workdict['Date'], website=workdict['Website'], thumbnail=workdict['Thumbnail'], bio=workdict['Bio'],description=workdict['Description'], extra=workdict['Extra'] )
# Process html
# parse workpage_html # process html: img full url
tree = html5lib.parse(workpage_html, namespaceHTMLElements=False)
imgs = tree.findall('.//img')
for img in imgs:
src = img.get('src')
newsrc = api_file_url(src)
# print 'new src', newsrc
if newsrc:
img.set('src', newsrc)
#print 'IMG', ET.tostring(img)
# save workpage_html
workpage_html = ET.tostring(tree)
#print 'TREE', workpage_html
# # save
work_filename = 'web/{}-{}-{}.html'.format(workdict['Date'], (workdict['Creator'].encode('ascii', 'ignore')).replace(' ','_'), pageid)
work_file = open(work_filename, "w")
work_file.write(workpage_html)
work_file.close()
'''

Write Preview
Loading…
Cancel
Save