github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-11 02:25:08 -05:00
Code Issues Projects Releases Packages Wiki Activity

[googleplus] Modernize and simplify

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-10 20:31:08 +01:00
parent 0de668af51
commit 3501423dfe
1 changed files with 27 additions and 32 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
youtube_dl/extractor/googleplus.py
View file

@ -1,4 +1,5 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals
import datetime import datetime
import re import re
@ -10,32 +11,28 @@
class GooglePlusIE(InfoExtractor): class GooglePlusIE(InfoExtractor):
IE_DESC = u'Google Plus' IE_DESC = 'Google Plus'
_VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)' _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
IE_NAME = u'plus.google' IE_NAME = 'plus.google'
_TEST = { _TEST = {
u"url": u"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH", 'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',
u"file": u"ZButuJc6CtH.flv", 'info_dict': {
u"info_dict": { 'id': 'ZButuJc6CtH',
u"upload_date": u"20120613", 'ext': 'flv',
u"uploader": u"井上ヨシマサ", 'upload_date': '20120613',
u"title": u"嘆きの天使 降臨" 'uploader': '井上ヨシマサ',
'title': '嘆きの天使 降臨',
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
# Extract id from URL # Extract id from URL
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
post_url = mobj.group(0) video_id = mobj.group('id')
video_id = mobj.group(1)
video_extension = 'flv'
# Step 1, Retrieve post webpage to extract further information # Step 1, Retrieve post webpage to extract further information
webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage') webpage = self._download_webpage(url, video_id, 'Downloading entry webpage')
self.report_extraction(video_id) self.report_extraction(video_id)
@ -43,7 +40,7 @@ def _real_extract(self, url):
upload_date = self._html_search_regex( upload_date = self._html_search_regex(
r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*> r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*>
([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''', ([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
webpage, u'upload date', fatal=False, flags=re.VERBOSE) webpage, 'upload date', fatal=False, flags=re.VERBOSE)
if upload_date: if upload_date:
# Convert timestring to a format suitable for filename # Convert timestring to a format suitable for filename
upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
@ -51,28 +48,27 @@ def _real_extract(self, url):
# Extract uploader # Extract uploader
uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>', uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
webpage, u'uploader', fatal=False) webpage, 'uploader', fatal=False)
# Extract title # Extract title
# Get the first line for title # Get the first line for title
video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]', video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
webpage, 'title', default=u'NA') webpage, 'title', default='NA')
# Step 2, Simulate clicking the image box to launch video # Step 2, Simulate clicking the image box to launch video
DOMAIN = 'https://plus.google.com/' DOMAIN = 'https://plus.google.com/'
video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN), video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
webpage, u'video page URL') webpage, 'video page URL')
if not video_page.startswith(DOMAIN): if not video_page.startswith(DOMAIN):
video_page = DOMAIN + video_page video_page = DOMAIN + video_page
webpage = self._download_webpage(video_page, video_id, u'Downloading video page') webpage = self._download_webpage(video_page, video_id, 'Downloading video page')
# Extract video links on video page # Extract video links all sizes
"""Extract video links of all sizes"""
pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"' pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
mobj = re.findall(pattern, webpage) mobj = re.findall(pattern, webpage)
if len(mobj) == 0: if len(mobj) == 0:
raise ExtractorError(u'Unable to extract video links') raise ExtractorError('Unable to extract video links')
# Sort in resolution # Sort in resolution
links = sorted(mobj) links = sorted(mobj)
@ -87,12 +83,11 @@ def _real_extract(self, url):
except AttributeError: # Python 3 except AttributeError: # Python 3
video_url = bytes(video_url, 'ascii').decode('unicode-escape') video_url = bytes(video_url, 'ascii').decode('unicode-escape')
return {
return [{
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'uploader': uploader, 'uploader': uploader,
'upload_date': upload_date, 'upload_date': upload_date,
'title': video_title, 'title': video_title,
'ext': video_extension, 'ext': 'flv',
}] }