Fix Threads post text extraction
This commit is contained in:
parent
bedeb8495d
commit
ece11a8352
4 changed files with 52 additions and 2 deletions
|
|
@ -16,6 +16,23 @@
|
|||
"idAttributes": ["data-id"],
|
||||
"permalinkSelectors": ["a.status__relative-time[href]", "a.detailed-status__datetime[href]", "a.u-url.u-uid[href]"]
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "threads",
|
||||
"name": "Threads",
|
||||
"urlPatterns": [
|
||||
"https://threads.com/*",
|
||||
"https://www.threads.com/*",
|
||||
"https://threads.net/*",
|
||||
"https://www.threads.net/*"
|
||||
],
|
||||
"requiredSelectors": ["[data-pressable-container=\"true\"], [role=\"article\"], article"],
|
||||
"post": {
|
||||
"rootSelectors": ["[data-pressable-container=\"true\"]", "[role=\"article\"]", "article"],
|
||||
"textSelectors": ["span[dir=\"auto\"]:not(a span):not(time span):not([role=\"button\"] span)"],
|
||||
"excludedSelectors": ["button", "[role=\"button\"]", "time", "svg"],
|
||||
"permalinkSelectors": ["a[href*=\"/post/\"]"]
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue