PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-03 08:43:58 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[ixigua] fix URL request error and video download error and video encryption parameters acquisition

Browse Source
This commit is contained in:
perror 2018-02-28 16:45:48 +08:00
parent 87e3bd5722
commit 0b50fdfab4
1 changed files with 28 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
src/you_get/extractors/ixigua.py
View File

@ -5,30 +5,35 @@ import random
import binascii import binascii
from ..common import * from ..common import *
def get_video_id(text): headers = {
re_id = r"videoId: '(.*?)'" 'User-Agent': 'Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36'
return re.findall(re_id, text)[0] ' (KHTML, like Gecko) Chrome/61.0.3163.100 Mobile Safari/537.36'
}
def get_r(): def get_r():
return str(random.random())[2:] return str(random.random())[2:]
def right_shift(val, n): def right_shift(val, n):
return val >> n if val >= 0 else (val + 0x100000000) >> n return val >> n if val >= 0 else (val + 0x100000000) >> n
def get_s(text): def get_s(text):
"""get video info""" """get video info"""
id = get_video_id(text) js_data = json.loads(text)
id = js_data['data']['video_id']
p = get_r() p = get_r()
url = 'http://i.snssdk.com/video/urls/v/1/toutiao/mp4/%s' % id url = 'http://i.snssdk.com/video/urls/v/1/toutiao/mp4/%s' % id
n = parse.urlparse(url).path + '?r=%s' % p n = parse.urlparse(url).path + '?r=%s' % p
c = binascii.crc32(n.encode('utf-8')) c = binascii.crc32(n.encode('utf-8'))
s = right_shift(c, 0) s = right_shift(c, 0)
title = ''.join(re.findall(r"title: '(.*?)',", text)) return url + '?r=%s&s=%s' % (p, s), js_data['data']['title']
return url + '?r=%s&s=%s' % (p, s), title
def get_moment(url, user_id, base_url, video_list): def get_moment(url, user_id, base_url, video_list):
"""Recursively obtaining a video list""" """Recursively obtaining a video list"""
video_list_data = json.loads(get_content(url)) video_list_data = json.loads(get_content(url, headers=headers))
if not video_list_data['next']['max_behot_time']: if not video_list_data['next']['max_behot_time']:
return video_list return video_list
[video_list.append(i["display_url"]) for i in video_list_data["data"]] [video_list.append(i["display_url"]) for i in video_list_data["data"]]
@ -41,23 +46,33 @@ def get_moment(url, user_id, base_url, video_list):
} }
return get_moment(**_param) return get_moment(**_param)
def ixigua_download(url, output_dir='.', info_only=False, **kwargs): def ixigua_download(url, output_dir='.', info_only=False, **kwargs):
""" Download a single video """ Download a single video
Sample URL: https://www.ixigua.com/a6487187567887254029/#mid=59051127876 Sample URL: https://www.ixigua.com/a6487187567887254029/#mid=59051127876
""" """
try: try:
video_info_url, title = get_s(get_content(url)) video_page_id = re.findall('(\d+)', [i for i in url.split('/') if i][3])[0] if 'toutiao.com' in url \
video_info = json.loads(get_content(video_info_url)) else re.findall('(\d+)', [i for i in url.split('/') if i][2])[0]
video_start_info_url = r'https://m.ixigua.com/i{}/info/'.format(video_page_id)
video_info_url, title = get_s(get_content(video_start_info_url, headers=headers or kwargs.get('headers', {})))
video_info = json.loads(get_content(video_info_url, headers=headers or kwargs.get('headers', {})))
except Exception: except Exception:
raise NotImplementedError(url) raise NotImplementedError(url)
try: try:
video_url = base64.b64decode(video_info["data"]["video_list"]["video_1"]["main_url"]).decode() video_url = base64.b64decode(video_info["data"]["video_list"]["video_1"]["main_url"]).decode()
except Exception: except Exception:
raise NotImplementedError(url) raise NotImplementedError(url)
filetype, ext, size = url_info(video_url) filetype, ext, size = url_info(video_url, headers=headers or kwargs.get('headers', {}))
print_info(site_info, title, filetype, size) print_info(site_info, title, filetype, size)
if not info_only: if not info_only:
download_urls([video_url], title, ext, size, output_dir=output_dir) _param = {
'output_dir': output_dir,
'headers': headers or kwargs.get('headers', {})
}
download_urls([video_url], title, ext, size, **_param)
def ixigua_download_playlist(url, output_dir='.', info_only=False, **kwargs): def ixigua_download_playlist(url, output_dir='.', info_only=False, **kwargs):
"""Download all video from the user's video list """Download all video from the user's video list
@ -80,6 +95,7 @@ def ixigua_download_playlist(url, output_dir='.', info_only=False, **kwargs):
for i in get_moment(**_param): for i in get_moment(**_param):
ixigua_download(i, output_dir, info_only, **kwargs) ixigua_download(i, output_dir, info_only, **kwargs)
site_info = "ixigua.com" site_info = "ixigua.com"
download = ixigua_download download = ixigua_download
download_playlist = ixigua_download_playlist download_playlist = ixigua_download_playlist