Download Jar. Libraryless. Click here for Pure Java version (5449L/37K).
1 | !7 |
2 | |
3 | p {
|
4 | S query = "gramophone"; |
5 | S userAgent = "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:53.0) Gecko/20100101 Firefox/53.0"; |
6 | S html = loadPageWithUserAgent("http://google.com/search?q=" + urlencode(query) + "&lr=lang_en&hl=en", userAgent);
|
7 | S url = first(loadPage_responseHeaders->get("Location"));
|
8 | if (url != null) |
9 | html = loadPageWithUserAgent(url, userAgent); |
10 | //print(html); |
11 | pnlStruct(loadPage_responseHeaders!); |
12 | |
13 | // Every h3 is a search result |
14 | L<S> htmlTok = htmlTok(html); |
15 | LL<S> h3s = findContainerTagDeep(htmlTok, "h3"); |
16 | pnlStruct(h3s); |
17 | for (L<S> tok : h3s) {
|
18 | L<S> linkTok = first(findContainerTag(tok, "a")); |
19 | if (empty(linkTok)) continue; |
20 | |
21 | S link = tagGet(second(linkTok), "href"); |
22 | S text = join(dropTags(contentsOfContainerTag(linkTok))); |
23 | L<S> sub = subList(htmlTok, magicIndexOfSubList(htmlTok, tok)+l(tok)-1); |
24 | S desc = trim(htmldecode(dropTags(join(first(findContainerTagWithParams(sub, "span", "class" := "st")))))); |
25 | |
26 | print("Link: " + link);
|
27 | print(" Text: " + text);
|
28 | print(" Desc: " + desc);
|
29 | } |
30 | } |
download show line numbers debug dex old transpilations
Travelled to 13 computer(s): aoiabmzegqzx, bhatertpkbcr, cbybwowwnfue, cfunsshuasjs, gwrvuhgaqvyk, ishqpsrjomds, lpdgvwnxivlt, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tslmcundralx, tvejysmllsmz, vouqrxazstgt
No comments. add comment
| Snippet ID: | #1011236 |
| Snippet name: | Scrape Google Spike [OK] |
| Eternal ID of this version: | #1011236/19 |
| Text MD5: | a9c63f65d196a19c0e501e4037e3a861 |
| Transpilation MD5: | d9873086d1d0da7681f357242c2010b2 |
| Author: | stefan |
| Category: | javax / networking |
| Type: | JavaX source code (desktop) |
| Public (visible to everyone): | Yes |
| Archived (hidden from active list): | No |
| Created/modified: | 2017-11-14 09:06:41 |
| Source code size: | 1113 bytes / 30 lines |
| Pitched / IR pitched: | No / No |
| Views / Downloads: | 571 / 1271 |
| Version history: | 18 change(s) |
| Referenced in: | [show references] |