Saverr/svtplay-dl
1
0
Fork 0
mirror of https://github.com/spaam/svtplay-dl.git synced 2024-11-24 04:05:39 +01:00
Code Issues Projects Releases Wiki Activity

Split out opengraph getter to separate function

Browse Source 
...and add doctests
This commit is contained in:
Anders Waldenborg 2014-02-18 16:17:02 +01:00
parent 5fe5eb40f2
commit 904e16d457
1 changed files with 23 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
lib/svtplay_dl/service/__init__.py
View File

@ -39,20 +39,35 @@ class Service(object):
pass
def opengraph_get(html, prop):
"""
Extract specified OpenGraph property from html.
>>> opengraph_get('<html><head><meta property="og:image" content="http://example.com/img.jpg"><meta ...', "image")
'http://example.com/img.jpg'
>>> opengraph_get('<html><head><meta content="http://example.com/img2.jpg" property="og:image"><meta ...', "image")
'http://example.com/img2.jpg'
>>> opengraph_get('<html><head><meta name="og:image" property="og:image" content="http://example.com/img3.jpg"><meta ...', "image")
'http://example.com/img3.jpg'
"""
match = re.search('<meta [^>]*property="og:' + prop + '" content="([^"]*)"', html)
if match is None:
match = re.search('<meta [^>]*content="([^"]*)" property="og:' + prop + '"', html)
if match is None:
return None
return match.group(1)
class OpenGraphThumbMixin(object):
"""
Mix this into the service class to grab thumbnail from OpenGraph properties.
"""
def get_thumbnail(self, options):
data = get_http_data(self.url)
match = re.search(r'<meta property="og:image" content="([^"]*)"', data)
if match is None:
match = re.search(r'<meta content="([^"]*)" property="og:image"', data)
if match is None:
match = re.search(r'<meta name="og:image" property="og:image" content="([^"]*)" />', data)
if match is None:
return
download_thumbnail(options, match.group(1))
url = opengraph_get(data, "image")
if url is None:
return
download_thumbnail(options, url)
from svtplay_dl.service.aftonbladet import Aftonbladet