用 python 来获取常用的微信/公众号回复emoji表情

2019-06-11 分类：后端之路 / 软件工具阅读(1038) 评论(0)

最近又个小需求来做微信相关的, 又开始找表情了.如图这样

每次需要的时候都要去网上找表情代码,太麻烦了. 所以就写了个个很简单的python爬虫抓了一些表情数据, 顺便熟悉一下python

from pyquery import PyQuery as pq
import demjson
urls = 'http://www.luxuqing.com/emoji/index.html'
dom = pq(url=urls, encoding='UTF-8')
itemList = dom.find('table tbody tr')
emoji = []
for index in range(0, len(itemList)):
    if index <= 1000:
        domData = itemList.eq(index)
        tdDom = domData.find('td')
        emojiArr = []
        for item in range(0, len(tdDom)):
            emojiArr.append(tdDom.eq(item).html())
        emoji.append(emojiArr)

jsonStr = demjson.encode(emoji)
open('emoji.json', 'a+').write(jsonStr)

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

from pyquery import PyQuery as pq

import demjson

urls = 'http://www.luxuqing.com/emoji/index.html'

dom = pq(url=urls, encoding='UTF-8')

itemList = dom.find('table tbody tr')

emoji = []

for index in range(0, len(itemList)):

if index <= 1000:

domData = itemList.eq(index)

tdDom = domData.find('td')

emojiArr = []

for item in range(0, len(tdDom)):

emojiArr.append(tdDom.eq(item).html())

emoji.append(emojiArr)

jsonStr = demjson.encode(emoji)

open('emoji.json', 'a+').write(jsonStr)

代码就简单的17行,爬到了这个页面上所有的表情数据( if index <= 1000: 是调试用的, 可忽略)

[
        "<span class=\"emoji   emoji2614\"/>",
        "umbrella with rain drops",
        "U+2614",
        "U+E640",
        "U+E48C",
        "U+E04B",
        "U+FE002",
        "☔"
    ],
    [
        "<span class=\"emoji   emoji26C4\"/>",
        "snowman without snow",
        "U+26C4",
        "U+E641",
        "U+E485",
        "U+E048",
        "U+FE003",
        "⛄"
    ],
.....

1

2

3

4

5

6

7

8

9

10

11

12