Question

这里有新的Python开发人员，我编写了这段简单的代码。

import requests
from bs4 import BeautifulSoup

def ColorRequest():
    url = 'http://csgoroll.com/v1/roulette/state?token=xxx' # Could add a + pls str(pagesomething) to add on to the url so that it would update
    sourcecode = requests.get(url) #requests the data from the site
    plaintext = sourcecode.text #imports all of the data gathered
    soup = BeautifulSoup(plaintext, 'lxml.parser') #This hold all of the data, and allows you to sort through all of the data, converts it
    for links in soup.findAll():
        print(links)

ColorRequest()

这导致这个页面给了我一些信息

{
    "gameState": "2",
    "currentGame": "9965904",
"startDate": "Mon Dec 05 2016 19:57:25 GMT+0000 (UTC)",
"rolls": [
    {
        "id": 9965905,
        "hash": "f73d96099b1d0e56c1499c81a3d6d595315109b0616f68964186b515944f9005",
        "roll": 1,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965906,
        "hash": "b17c139731e2404ac3c2c791b1063885e639886ada49a3c51ea05381fcc774e2",
        "roll": 6,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965907,
        "hash": "8affa37e1b3ecc1a3201c36dcfc6e670725b209565a345b4df71242d68a043f2",
        "roll": 14,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965908,
        "hash": "755f7895e1f39835679753c881529ea88d37cec730a1d73fcd97155797fdf7d4",
        "roll": 13,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965909,
        "hash": "949b3e0141fce775b5f08debac3ee83cfe8135a1f4fa5ebfa7e110c21e2d8330",
        "roll": 12,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965910,
        "hash": "258c9a9dc3f46dd2de4746ce810f751fd1e175b00233268558cf70ad9ed750bb",
        "roll": 13,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965911,
        "hash": "61d20e3ff8da82bf0717505272ec41ea13801fd6f72d65d2562208664e47171e",
        "roll": 1,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965912,
        "hash": "ed922d803ef9d2d182bc68caad725c3b95722a9223ded6b544b0c715a58f7544",
        "roll": 9,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965913,
        "hash": "480f5cfb5fcd2483d08591f68021bdbc530696e7bad366414fb6fb1704cc45e5",
        "roll": 14,
        "state": 3,
        "created_at": null,
        "updated_at": null
    },
    {
        "id": 9965914,
        "hash": "31b9299695e4090e840ad2b1afb2f6d5840cb46cb2f028df8e5f539ecb3e8027",
        "roll": 2,
        "state": 3,
        "created_at": null,
        "updated_at": null
    }

我对页面抓取很新，我想问一下为什么我的html刮刀无法获取所提供的数据？这可能是什么语言 - 如果它不是一种语言，我可以做些什么来纠正我的代码，以便我的程序将来能够阅读它？

Answer 1

数据为JSON，而非HTML。代码的工作片段可能如下所示：

import requests
import json

def ColorRequest():
    url = 'http://csgoroll.com/v1/roulette/state?token=xxx' # Could add a + pls str(pagesomething) to add on to the url so that it would update
    sourcecode = requests.get(url) #requests the data from the site
    plaintext = sourcecode.text #imports all of the data gathered

    obj = json.loads(plaintext)
    for roll in obj['rolls']:
        print(roll)


if __name__ == '__main__':
    ColorRequest()

Page Scraping，但是html解释器失败了吗？

1 个答案: