Libraryless. Click here for Pure Java version (2435L/17K/54K).
1 | !752 |
2 | |
3 | p {
|
4 | S username = "stefanreich"; |
5 | Map<S, O> data = loadMediumJSON(username); |
6 | printStructureLines(data); |
7 | |
8 | pcall {
|
9 | Map user = (Map) data.get("user");
|
10 | print("Name: " + user.get("name"));
|
11 | print("Bio: " + user.get("bio"));
|
12 | print("Image ID: " + user.get("imageid"));
|
13 | // Could do more here, like Twitter name |
14 | } |
15 | |
16 | pcall {
|
17 | L streamItems = (L) data.get("streamItems");
|
18 | for i over streamItems: {
|
19 | print("Stream item #" + i);
|
20 | Map item = (Map) streamItems.get(i); |
21 | Map preview = (Map) item.get("postPreview");
|
22 | psl(preview); |
23 | if (preview != null) {
|
24 | S postID = getString(preview, "postId"); |
25 | Map post = (Map) preview.get("post");
|
26 | //psl(post); |
27 | print("Post ID: " + postID);
|
28 | S uniqueSlug = getString(post, "uniqueSlug"); |
29 | S link = "https://medium.com/@" + username + "/" + uniqueSlug; |
30 | S title = getString(post, "title"); |
31 | print("Title: " + title);
|
32 | print("Probable link: " + link);
|
33 | psl(post); |
34 | } |
35 | print(); |
36 | } |
37 | } |
38 | } |
39 | |
40 | sbool loadMediumJSON_verbose; |
41 | |
42 | static Map<S, O> loadMediumJSON(S username) {
|
43 | S html = loadPageWithUserAgent("https://medium.com/@" + username, "Mac Safari");
|
44 | if (loadMediumJSON_verbose) print(html); |
45 | |
46 | S prefix = [[window["obvInit"](]]; |
47 | int i = indexOf(html, prefix); |
48 | if (i < 0) null; |
49 | int j = indexOf(html, "\n", i); |
50 | if (j < 0) null; |
51 | S json = dropSuffix(")", trim(substring(html, i+l(prefix), j)));
|
52 | ret jsonDecodeMap(json); |
53 | } |
download show line numbers debug dex old transpilations
Travelled to 14 computer(s): aoiabmzegqzx, bhatertpkbcr, cbybwowwnfue, cfunsshuasjs, ddnzoavkxhuk, gwrvuhgaqvyk, ishqpsrjomds, lpdgvwnxivlt, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tslmcundralx, tvejysmllsmz, vouqrxazstgt
No comments. add comment
| Snippet ID: | #1004101 |
| Snippet name: | Try scraping medium.com - using streamItems, stopped working |
| Eternal ID of this version: | #1004101/1 |
| Text MD5: | 831f4f1a066139c88a8ef70483af2a44 |
| Transpilation MD5: | 3de7994e59212667ede5c3c61ca517e3 |
| Author: | stefan |
| Category: | javax / networking |
| Type: | JavaX source code |
| Public (visible to everyone): | Yes |
| Archived (hidden from active list): | No |
| Created/modified: | 2016-10-04 21:48:40 |
| Source code size: | 1556 bytes / 53 lines |
| Pitched / IR pitched: | No / No |
| Views / Downloads: | 839 / 973 |
| Referenced in: | [show references] |