fix(web): update sogou search regex to match new HTML structure (#3139)
- reSogouTitle: make class attribute quotes optional (class="?resultLink"?) - reSogouSnippet: allow additional CSS classes after clamp (clamp\d*[^"]*) Sogou WAP search page changed its HTML format: - class=resultLink -> class="resultLink" (added quotes) - class="clamp3" -> class="clamp2 fz-mid click-sugg-content" (extra classes) Fixes web_search tool failing to parse sogou search results.
This commit is contained in:
parent
1420875921
commit
7b5fe01187
1 changed files with 2 additions and 2 deletions
|
|
@ -55,9 +55,9 @@ var (
|
||||||
`<a class="result__snippet[^"]*".*?>([\s\S]*?)</a>`,
|
`<a class="result__snippet[^"]*".*?>([\s\S]*?)</a>`,
|
||||||
)
|
)
|
||||||
reSogouTitle = regexp.MustCompile(
|
reSogouTitle = regexp.MustCompile(
|
||||||
`<a\s+class=resultLink\s+href="([^"]+)"[^>]*id="sogou_vr_\d+_\d+"[^>]*>\s*(.*?)\s*</a>`,
|
`<a\s+class="?resultLink"?\s+href="([^"]+)"[^>]*id="sogou_vr_\d+_\d+"[^>]*>\s*(.*?)\s*</a>`,
|
||||||
)
|
)
|
||||||
reSogouSnippet = regexp.MustCompile(`<div class="clamp\d*">\s*(.*?)\s*</div>`)
|
reSogouSnippet = regexp.MustCompile(`<div class="clamp\d*[^"]*">\s*(.*?)\s*</div>`)
|
||||||
reSogouRealURL = regexp.MustCompile(`url=([^&]+)`)
|
reSogouRealURL = regexp.MustCompile(`url=([^&]+)`)
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue