Created
November 16, 2018 12:29
-
-
Save tesths/fbbb70b99af523d8b4eaaa939e648d57 to your computer and use it in GitHub Desktop.
SanaChina961229 Web Scraper
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"_id": "weibo", | |
"startUrl": [ | |
"https://weibo.com/SanaChina961229?is_search=0&visible=0&is_all=1&is_tag=0&profile_ftype=1&page=[1-2]" | |
], | |
"selectors": [ | |
{ | |
"id": "real-content", | |
"type": "SelectorElementScroll", | |
"parentSelectors": [ | |
"_root" | |
], | |
"selector": "div.WB_cardwrap.WB_feed_type.S_bg2", | |
"multiple": true, | |
"delay": "15000" | |
}, | |
{ | |
"id": "content1", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"real-content" | |
], | |
"selector": "div.WB_text.W_f14", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
}, | |
{ | |
"id": "@someone", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"real-content" | |
], | |
"selector": "div.WB_expand div.WB_info", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
}, | |
{ | |
"id": "forward", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"real-content" | |
], | |
"selector": "div.WB_expand div.WB_text", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
}, | |
{ | |
"id": "link", | |
"type": "SelectorLink", | |
"parentSelectors": [ | |
"real-content" | |
], | |
"selector": "div.WB_text a", | |
"multiple": false, | |
"delay": 0 | |
}, | |
{ | |
"id": "picture", | |
"type": "SelectorImage", | |
"parentSelectors": [ | |
"real-content" | |
], | |
"selector": "li.WB_pic img", | |
"multiple": false, | |
"delay": 0 | |
}, | |
{ | |
"id": "group", | |
"type": "SelectorHTML", | |
"parentSelectors": [ | |
"real-content" | |
], | |
"selector": "div.WB_media_wrap.clearfix", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
}, | |
{ | |
"id": "time", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"real-content" | |
], | |
"selector": "div.WB_from a.S_txt2:nth-of-type(1)", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment