Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[extractor/iqiyi] Fix Iq JS regex #5922

Merged
merged 3 commits into from
Jan 2, 2023
+12 −9
Merged

[extractor/iqiyi] Fix Iq JS regex #5922

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e3a5190
[extractor/iqiyi] Fix `Iq` JS regex
bashonly Jan 1, 2023
46d1113
Apply suggestions from code review
bashonly Jan 2, 2023
72c4205
Cleanup
bashonly Jan 2, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
21 changes: 12 additions & 9 deletions yt_dlp/extractor/iqiyi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -527,11 +527,14 @@ def _extract_vms_player_js(self, webpage, video_id):
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.cache.store('iq', 'player_js', module_js)
Expand All @@ -543,11 +546,11 @@ def _extract_cmd5x_function(self, webpage, video_id):
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 = {
Expand Down