Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-13 13:37:15 +08:00
Code Issues Releases Wiki Activity

[aliexpress] rewrote code so that it parses JSON

Browse Source
This commit is contained in:
dubber0 2017-07-23 15:35:28 +02:00
parent 9e8c64cb0c
commit 4b990cb33a
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/aliexpress.py
View File

@ -8,7 +8,7 @@ from datetime import datetime
class AliExpressLiveIE(InfoExtractor): class AliExpressLiveIE(InfoExtractor):
_VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>[0-9]{16})' _VALID_URL = r'https?://live\.aliexpress\.com/live/(?P<id>[0-9]{16})'
_TEST = [{ _TEST = {
'url': 'https://live.aliexpress.com/live/2800002704436634', 'url': 'https://live.aliexpress.com/live/2800002704436634',
'info_dict': { 'info_dict': {
'id': '2800002704436634', 'id': '2800002704436634',
@ -21,17 +21,23 @@ class AliExpressLiveIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
} }
}] }
def _real_extract(self, url): def _real_extract(self, url):
page = self._download_webpage(url, self._match_id(url)) vid_id = str(self._match_id(url))
upload_date = self._html_search_regex(r'"createTime":([0-9]{10})[0-9]{3},', page, 'upload_date') page = self._download_webpage(url, self._match_id(url)).replace('\n', '')
# runParams is a variable which contains information about the stream
run_params_json = self._search_regex(r'runParams = ([^<]+)[\s+]var [a-z]+', page, 'runParams')
run_params = self._parse_json(run_params_json, vid_id)
# the given unix timestamp contains 000 at the end, so we have to strip it off by dividing it with 1000
upload_date = datetime.fromtimestamp(run_params.get('followBar').get('createTime') / 1000).strftime('%Y%m%d')
return { return {
'id': str(self._match_id(url)), 'id': vid_id,
'title': self._html_search_regex(r'"title": "([^"]+)"', page, 'url'), 'title': run_params['title'],
'url': self._html_search_regex(r'"replyStreamUrl": "([^"]+)"', page, 'url'), 'url': run_params['replyStreamUrl'],
'uploader': self._html_search_regex(r'"name":"([^"]+)"', page, 'uploader'), 'uploader': run_params.get('followBar').get('name'),
'upload_date': datetime.fromtimestamp(int(upload_date)).strftime('%Y%m%d'), 'upload_date': upload_date,
'is_live': True, 'is_live': True,
} }