全文簡介

本文是先采集拉勾網(wǎng)上面的數(shù)據(jù)，采集的是Python崗位的數(shù)據(jù)，然后用Python進(jìn)行可視化。主要涉及的是爬蟲&數(shù)據(jù)可視化的知識。

爬蟲部分

先用Python來抓取拉勾網(wǎng)上面的數(shù)據(jù)，采用的是簡單好用的requests模塊。主要注意的地方是，拉勾網(wǎng)屬于動態(tài)網(wǎng)頁，所以會用到瀏覽器的F12開發(fā)者工具進(jìn)行抓包。抓包以后會發(fā)現(xiàn)，其實網(wǎng)頁是一個POST的形式，所以要提交數(shù)據(jù)，提交的數(shù)據(jù)如下圖：

真實網(wǎng)址是：

https://www.lagou.com/jobs/positionAjax.jsonneedAddtionalResult=false&isSchoolJob=0

在上圖也可以輕松發(fā)現(xiàn)：kd是查詢關(guān)鍵詞，pn是頁數(shù)，可以實現(xiàn)翻頁。

代碼實現(xiàn)

import requests # 網(wǎng)絡(luò)請求

import re

import time

import random

# post的網(wǎng)址

url = 'https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false&isSchoolJob=0'

# 反爬措施

header = {'Host': 'www.lagou.com',

'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36',

'Accept': 'application/json, text/javascript, */*; q=0.01',

'Accept-Language': 'zh-CN,en-US;q=0.7,en;q=0.3',

'Accept-Encoding': 'gzip, deflate, br',

'Referer': 'https://www.lagou.com/jobs/list_Python?labelWords=&fromSearch=true&suginput=',

'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',

'X-Requested-With': 'XMLHttpRequest',

'X-Anit-Forge-Token': 'None',

'X-Anit-Forge-Code': '0',

'Content-Length': '26',

'Cookie': 'user_trace_token=20171103191801-9206e24f-9ca2-40ab-95a3-23947c0b972a; _ga=GA1.2.545192972.1509707889; LGUID=20171103191805-a9838dac-c088-11e7-9704-5254005c3644; JSESSIONID=ABAAABAACDBABJB2EE720304E451B2CEFA1723CE83F19CC; _gat=1; LGSID=20171228225143-9edb51dd-ebde-11e7-b670-525400f775ce; PRE_UTM=; PRE_HOST=www.baidu.com; PRE_SITE=https%3A%2F%2Fwww.baidu.com%2Flink%3Furl%3DKkJPgBHAnny1nUKaLpx2oDfUXv9ItIF3kBAWM2-fDNu%26ck%3D3065.1.126.376.140.374.139.129%26shh%3Dwww.baidu.com%26sht%3Dmonline_3_dg%26wd%3D%26eqid%3Db0ec59d100013c7f000000055a4504f6; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2F; LGRID=20171228225224-b6cc7abd-ebde-11e7-9f67-5254005c3644; index_location_city=%E5%85%A8%E5%9B%BD; TG-TRACK-CODE=index_search; SEARCH_ID=3ec21cea985a4a5fa2ab279d868560c8',

'Connection': 'keep-alive',

'Pragma': 'no-cache',

'Cache-Control': 'no-cache'}

for n in range(30):

# 要提交的數(shù)據(jù)

form = {'first':'false',

'kd':'Python',

'pn':str(n)}

time.sleep(random.randint(2,5))

# 提交數(shù)據(jù)

html = requests.post(url,data=form,headers = header)

# 提取數(shù)據(jù)

data = re.findall('{"companyId":.*?,"positionName":"(.*?)","workYear":"(.*?)","education":"(.*?)","jobNature":"(.*?)","financeStage":"(.*?)","companyLogo":".*?","industryField":".*?","city":"(.*?)","salary":"(.*?)","positionId":.*?,"positionAdvantage":"(.*?)","companyShortName":"(.*?)","district"',html.text)

# 轉(zhuǎn)換成數(shù)據(jù)框

data = pd.DataFrame(data)

# 保存在本地

data.to_csv(r'D:Windows 7 DocumentsDesktopMyLaGouDataMatlab.csv',header = False, index = False, mode = 'a+')

注意：抓取數(shù)據(jù)的時候不要爬取太快，除非你有其他的反爬措施，比如更換IP等，另外不需登錄，我在代碼加入了time模塊，用于限制爬取速度。

數(shù)據(jù)可視化

下載下來的數(shù)據(jù)長成這個樣子：

注意標(biāo)題（也就是列明）是我自己添加的。

導(dǎo)入模塊并配置繪圖風(fēng)格

import pandas as pd # 數(shù)據(jù)框操作

import numpy as np

import matplotlib.pyplot as plt # 繪圖

import jieba # 分詞

from wordcloud importWordCloud# 詞云可視化

import matplotlib as mpl # 配置字體

from pyecharts importGeo# 地理圖

mpl.rcParams["font.sans-serif"] = ["Microsoft YaHei"]

# 配置繪圖風(fēng)格

plt.rcParams["axes.labelsize"] = 16.

plt.rcParams["xtick.labelsize"] = 14.

plt.rcParams["ytick.labelsize"] = 14.

plt.rcParams["legend.fontsize"] = 12.

plt.rcParams["figure.figsize"] = [15., 15.]

注意：導(dǎo)入模塊的時候其他都容易解決，除了wordcloud這個模塊，這個模塊我建議大家手動安裝，如果pip安裝的話，會提示你缺少C++14.0之類的錯誤，導(dǎo)致安裝不上。手動下載whl文件就可以順利安裝了。

數(shù)據(jù)預(yù)覽

# 導(dǎo)入數(shù)據(jù)

data = pd.read_csv('D:Windows 7 DocumentsDesktopMyLaGouDataPython.csv',encoding='gbk') # 導(dǎo)入數(shù)據(jù)

data.head()

read_csv路徑不要帶有中文

data.tail()

學(xué)歷要求

data['學(xué)歷要求'].value_counts().plot(kind='barh',rot=0)

plt.show()

工作經(jīng)驗

data['工作經(jīng)驗'].value_counts().plot(kind='bar',rot=0,color='b')

plt.show()

Python熱門崗位

final = ''

stopwords = ['PYTHON','python','Python','工程師','（','）','/'] # 停止詞

for n in range(data.shape[0]):

seg_list = list(jieba.cut(data['崗位職稱'][n]))

for seg in seg_list:

if seg notin stopwords:

final = final + seg + ' '

# final 得到的詞匯

工作地點(diǎn)

data['工作地點(diǎn)'].value_counts().plot(kind='pie',autopct='%1.2f%%',explode = np.linspace(0,1.5,25))

plt.show()

工作地理圖

# 提取數(shù)據(jù)框

data2 = list(map(lambda x:(data['工作地點(diǎn)'][x],eval(re.split('k|K',data['工資'][x])[0])*1000),range(len(data))))

# 提取價格信息

data3 = pd.DataFrame(data2)

# 轉(zhuǎn)化成Geo需要的格式

data4 = list(map(lambda x:(data3.groupby(0).mean()[1].index[x],data3.groupby(0).mean()[1].values[x]),range(len(data3.groupby(0)))))

# 地理位置展示

geo = Geo("全國Python工資布局", "制作人:挖掘機(jī)小王子", title_color="#fff", title_pos="left", width=1200, height=600,

background_color='#404a59')

attr, value = geo.cast(data4)

geo.add("", attr, value, type="heatmap", is_visualmap=True, visual_range=[0, 300], visual_text_color='#fff')

# 中國地圖Python工資，此分布是最低薪資

geo