Worked on html scraping

This commit is contained in:
Lukas Wölfer
2025-10-02 21:43:29 +02:00
parent 95d13370c2
commit 28c4f4595e
4 changed files with 693 additions and 1 deletions

37
Cargo.lock generated
View File

@@ -462,6 +462,12 @@ dependencies = [
"dtoa",
]
[[package]]
name = "ego-tree"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b2972feb8dffe7bc8c5463b1dacda1b0dfbed3710e50f977d965429692d74cd8"
[[package]]
name = "either"
version = "1.15.0"
@@ -671,6 +677,15 @@ dependencies = [
"version_check",
]
[[package]]
name = "getopts"
version = "0.2.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cfe4fbac503b8d1f88e6676011885f34b7174f46e59956bba534ba83abded4df"
dependencies = [
"unicode-width",
]
[[package]]
name = "getrandom"
version = "0.2.16"
@@ -1983,6 +1998,21 @@ version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
[[package]]
name = "scraper"
version = "0.24.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5f3a24d916e78954af99281a455168d4a9515d65eca99a18da1b813689c4ad9"
dependencies = [
"cssparser",
"ego-tree",
"getopts",
"html5ever",
"precomputed-hash",
"selectors",
"tendril",
]
[[package]]
name = "security-framework"
version = "2.11.1"
@@ -2277,6 +2307,7 @@ dependencies = [
"mwbot",
"rand 0.9.2",
"reqwest",
"scraper",
"serde",
"thiserror 2.0.12",
"tokio",
@@ -2643,6 +2674,12 @@ version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512"
[[package]]
name = "unicode-width"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4a1a07cc7db3810833284e8d372ccdc6da29741639ecc70c9ec107df0fa6154c"
[[package]]
name = "untrusted"
version = "0.9.0"