-# coding: utf-8
-from __future__ import unicode_literals
-
import hashlib
import itertools
import re
return hashlib.md5(text.encode('utf-8')).hexdigest()
-class IqiyiSDK(object):
+class IqiyiSDK:
def __init__(self, target, ip, timestamp):
self.target = target
self.ip = ip
self.target = self.digit_sum(self.timestamp) + chunks[0] + compat_str(sum(ip))
-class IqiyiSDKInterpreter(object):
+class IqiyiSDKInterpreter:
def __init__(self, sdk_code):
self.sdk_code = sdk_code
self._sleep(5, video_id)
- self._sort_formats(formats)
title = (get_element_by_id('widget-videotitle', webpage)
or clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage))
or self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
'1': 'zh_CN',
'2': 'zh_TW',
'3': 'en',
+ '4': 'kor',
'18': 'th',
'21': 'my',
'23': 'vi',
'''
def _extract_vms_player_js(self, webpage, video_id):
- player_js_cache = self._downloader.cache.load('iq', 'player_js')
+ player_js_cache = self.cache.load('iq', 'player_js')
if player_js_cache:
return player_js_cache
webpack_js_url = self._proto_relative_url(self._search_regex(
r'<script src="((?:https?)?//stc.iqiyipic.com/_next/static/chunks/webpack-\w+\.js)"', webpage, 'webpack URL'))
webpack_js = self._download_webpage(webpack_js_url, video_id, note='Downloading webpack JS', errnote='Unable to download webpack JS')
- webpack_map1, webpack_map2 = [self._parse_json(js_map, video_id, transform_source=js_to_json) for js_map in self._search_regex(
- r'\(({[^}]*})\[\w+\][^\)]*\)\s*\+\s*["\']\.["\']\s*\+\s*({[^}]*})\[\w+\]\+["\']\.js', webpack_js, 'JS locations', group=(1, 2))]
- for module_index in reversed(list(webpack_map2.keys())):
+ webpack_map = self._search_json(
+ r'["\']\s*\+\s*', webpack_js, 'JS locations', video_id,
+ contains_pattern=r'{\s*(?:\d+\s*:\s*["\'][\da-f]+["\']\s*,?\s*)+}',
+ end_pattern=r'\[\w+\]\+["\']\.js', transform_source=js_to_json)
+
+ for module_index in reversed(webpack_map):
module_js = self._download_webpage(
- f'https://stc.iqiyipic.com/_next/static/chunks/{webpack_map1.get(module_index, module_index)}.{webpack_map2[module_index]}.js',
+ f'https://stc.iqiyipic.com/_next/static/chunks/{module_index}.{webpack_map[module_index]}.js',
video_id, note=f'Downloading #{module_index} module JS', errnote='Unable to download module JS', fatal=False) or ''
if 'vms request' in module_js:
- self._downloader.cache.store('iq', 'player_js', module_js)
+ self.cache.store('iq', 'player_js', module_js)
return module_js
raise ExtractorError('Unable to extract player JS')
self._extract_vms_player_js(webpage, video_id), 'signature function')
def _update_bid_tags(self, webpage, video_id):
- extracted_bid_tags = self._parse_json(
- self._search_regex(
- r'arguments\[1\][^,]*,\s*function\s*\([^\)]*\)\s*{\s*"use strict";?\s*var \w=({.+}})\s*,\s*\w\s*=\s*{\s*getNewVd',
- self._extract_vms_player_js(webpage, video_id), 'video tags', default=''),
- video_id, transform_source=js_to_json, fatal=False)
+ extracted_bid_tags = self._search_json(
+ r'function\s*\([^)]*\)\s*\{\s*"use strict";?\s*var \w\s*=\s*',
+ self._extract_vms_player_js(webpage, video_id), 'video tags', video_id,
+ contains_pattern=r'{\s*\d+\s*:\s*\{\s*nbid\s*:.+}\s*}',
+ end_pattern=r'\s*,\s*\w\s*=\s*\{\s*getNewVd', fatal=False, transform_source=js_to_json)
if not extracted_bid_tags:
return
self._BID_TAGS = {
ut_list = ['0']
# bid 0 as an initial format checker
- dash_paths = self._parse_json(PhantomJSwrapper(self).get(
- url, html='<!DOCTYPE html>', video_id=video_id, note2='Executing signature code', jscode=self._DASH_JS % {
+ dash_paths = self._parse_json(PhantomJSwrapper(self, timeout=120_000).get(
+ url, note2='Executing signature code (this may take a couple minutes)',
+ html='<!DOCTYPE html>', video_id=video_id, jscode=self._DASH_JS % {
'tvid': video_info['tvId'],
'vid': video_info['vid'],
'src': traverse_obj(next_props, ('initialProps', 'pageProps', 'ptid'),
preview_time = traverse_obj(
initial_format_data, ('boss_ts', (None, 'data'), ('previewTime', 'rtime')), expected_type=float_or_none, get_all=False)
if traverse_obj(initial_format_data, ('boss_ts', 'data', 'prv'), expected_type=int_or_none):
- self.report_warning('This preview video is limited%s' % format_field(preview_time, template=' to %s seconds'))
+ self.report_warning('This preview video is limited%s' % format_field(preview_time, None, ' to %s seconds'))
# TODO: Extract audio-only formats
for bid in set(traverse_obj(initial_format_data, ('program', 'video', ..., 'bid'), expected_type=str_or_none, default=[])):
})
formats.extend(extracted_formats)
- self._sort_formats(formats)
-
for sub_format in traverse_obj(initial_format_data, ('program', 'stl', ...), expected_type=dict, default=[]):
lang = self._LID_TAGS.get(str_or_none(sub_format.get('lid')), sub_format.get('_name'))
subtitles.setdefault(lang, []).extend([{