【7月最新实现】使用Python获取全网招聘数据，实现可视化分析
哈喽兄弟们，今天来实现采集一下最新的qcwu招聘数据。
因为网站嘛，大家都爬来爬去的，人家就会经常更新，所以代码对应的也要经常重新去写。
对于会的人来说，当然无所谓，任他更新也拦不住，但是对于不会的小伙伴来说，网站一更新，当场自闭。
所以这期是出给不会的小伙伴的，我还录制了视频进行详细讲解，跟源码一起打包好了，直接在文末名片自取。
软件工具
先来看看需要准备啥
环境使用
Python 3.8
Pycharm
模块使用
# 第三方模块 需要安装的
requests >>> pip install requests
csv
实现爬虫基本流程
一、数据来源分析: 思路固定
-
明确需求:
- 明确采集网站以及数据内容
网址: 51job
内容: 招聘信息 -
通过开发者工具, 进行抓包分析, 分析具体数据来源
I. 打开开发者工具: F12 / 右键点击检查选择network
II. 刷新网页, 让数据内容重新加载一遍
III. 通过搜索<搜索你要的数据>去找数据具体位置
招聘信息数据包: https://we.***.com/api/job/search-pc?api_key=51job×tamp=1688645783&keyword=python&searchType=2&function=&industry=&jobArea=010000%2C020000%2C030200%2C040000%2C090200&jobArea2=&landmark=&metro=&salary=&workYear=°ree=&companyType=&companySize=&jobType=&issueDate=&sortType=0&pageNum=1&requestId=&pageSize=20&source=1&accountId=&pageCode=sou%7Csou%7Csoulb
二、代码实现步骤: 步骤固定
- 发送请求, 模拟浏览器对于url地址发送请求
请求链接: 招聘信息数据包url - 获取数据, 获取服务器返回响应数据 <所有的数据>
开发者工具: response - 解析数据, 提取我们想要的数据内容
招聘基本信息 - 保存数据, 把信息数据保存表格文件里面
代码解析
模块
# 导入数据请求模块
import requests
# 导入格式化输出模块
from pprint import pprint
# 导入csv
import csv
发送请求, 模拟浏览器对于url地址发送请求
headers = {
'Cookie': 'guid=54b7a6c4c43a33111912f2b5ac6699e2; sajssdk_2015_cross_new_user=1; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2254b7a6c4c43a33111912f2b5ac6699e2%22%2C%22first_id%22%3A%221892b08f9d11c8-09728ce3464dad8-26031d51-3686400-1892b08f9d211e7%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%2C%22%24latest_referrer%22%3A%22%22%7D%2C%22identities%22%3A%22eyIkaWRlbnRpdHlfY29va2llX2lkIjoiMTg5MmIwOGY5ZDExYzgtMDk3MjhjZTM0NjRkYWQ4LTI2MDMxZDUxLTM2ODY0MDAtMTg5MmIwOGY5ZDIxMWU3IiwiJGlkZW50aXR5X2xvZ2luX2lkIjoiNTRiN2E2YzRjNDNhMzMxMTE5MTJmMmI1YWM2Njk5ZTIifQ%3D%3D%22%2C%22history_login_id%22%3A%7B%22name%22%3A%22%24identity_login_id%22%2C%22value%22%3A%2254b7a6c4c43a33111912f2b5ac6699e2%22%7D%2C%22%24device_id%22%3A%221892b08f9d11c8-09728ce3464dad8-26031d51-3686400-1892b08f9d211e7%22%7D; nsearch=jobarea%3D%26%7C%26ord_field%3D%26%7C%26recentSearch0%3D%26%7C%26recentSearch1%3D%26%7C%26recentSearch2%3D%26%7C%26recentSearch3%3D%26%7C%26recentSearch4%3D%26%7C%26collapse_expansion%3D; search=jobarea%7E%60010000%2C020000%2C030200%2C040000%2C090200%7C%21recentSearch0%7E%60010000%2C020000%2C030200%2C040000%2C090200%A1%FB%A1%FA000000%A1%FB%A1%FA0000%A1%FB%A1%FA00%A1%FB%A1%FA99%A1%FB%A1%FA%A1%FB%A1%FA99%A1%FB%A1%FA99%A1%FB%A1%FA99%A1%FB%A1%FA99%A1%FB%A1%FA9%A1%FB%A1%FA99%A1%FB%A1%FA%A1%FB%A1%FA0%A1%FB%A1%FApython%A1%FB%A1%FA2%A1%FB%A1%FA1%7C%21; privacy=1688644161; Hm_lvt_1370a11171bd6f2d9b1fe98951541941=1688644162; Hm_lpvt_1370a11171bd6f2d9b1fe98951541941=1688644162; JSESSIONID=BA027715BD408799648B89C132AE93BF; acw_tc=ac11000116886495592254609e00df047e220754059e92f8a06d43bc419f21; ssxmod_itna=Qqmx0Q0=K7qeqD5itDXDnBAtKeRjbDce3=e8i=Ax0vTYPGzDAxn40iDtrrkxhziBemeLtE3Yqq6j7rEwPeoiG23pAjix0aDbqGkPA0G4GG0xBYDQxAYDGDDPDocPD1D3qDkD7h6CMy1qGWDm4kDWPDYxDrjOKDRxi7DDvQkx07DQ5kQQGxjpBF=FHpu=i+tBDkD7ypDlaYj9Om6/fxMp7Ev3B3Ix0kl40Oya5s1aoDUlFsBoYPe723tT2NiirY6QiebnnDsAhWC5xyVBDxi74qTZbKAjtDirGn8YD===; ssxmod_itna2=Qqmx0Q0=K7qeqD5itDXDnBAtKeRjbDce3=e8i=DnIfwqxDstKhDL0iWMKV3Ekpun3DwODKGcDYIxxD==; acw_sc__v2=64a6bf58f0b7feda5038718459a3b1e625849fa8',
'Referer': 'https://we.51job.com/pc/search?jobArea=010000,020000,030200,040000,090200&keyword=python&searchType=2&sortType=0&metro=',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
}
# 请求链接
url = 'https://we.***.com/api/job/search-pc'
# 请求参数
data = {
'api_key': '51job',
'timestamp': '*****',
'keyword': '****',
'searchType': '2',
'function': '',
'industry': '',
'jobArea': '010000,020000,030200,040000,090200',
'jobArea2': '',
'landmark': '',
'metro': '',
'salary': '',
'workYear': '',
'degree': '',
'companyType': '',
'companySize': '',
'jobType': '',
'issueDate': '',
'sortType': '0',
'pageNum': '1',
'requestId': '',
'pageSize': '20',
'source': '1',
'accountId': '',
'pageCode': 'sou|sou|soulb',
}
# 发送请求
response = requests.get(url=url, params=data, headers=headers)
获取数据
获取服务器返回响应数据 <所有的数据>
开发者工具: response
- response.json() 获取响应json数据
解析数据
提取我们想要的数据内容
for循环遍历
for index in response.json()['resultbody']['job']['items']:
# index 具体岗位信息 --> 字典
dit = {
'职位': index['jobName'],
'公司': index['fullCompanyName'],
'薪资': index['provideSalaryString'],
'城市': index['jobAreaString'],
'经验': index['workYearString'],
'学历': index['degreeString'],
'公司性质': index['companyTypeString'],
'公司规模': index['companySizeString'],
'职位详情页': index['jobHref'],
'公司详情页': index['companyHref'],
}
以字典方式进行数据保存
csv_writer.writerow(dit)
print(dit)
保存表格
f = open('python.csv', mode='w', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
'职位',
'公司',
'薪资',
'城市',
'经验',
'学历',
'公司性质',
'公司规模',
'职位详情页',
'公司详情页',
])
csv_writer.writeheader()
可视化部分
import pandas as pd
df = pd.read_csv('data.csv')
df.head()
df['学历'] = df['学历'].fillna('不限学历')
edu_type = df['学历'].value_counts().index.to_list()
edu_num = df['学历'].value_counts().to_list()
from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
from pyecharts.globals import CurrentConfig, NotebookType
CurrentConfig.NOTEBOOK_TYPE = NotebookType.JUPYTER_LAB
c = (
Pie()
.add(
"",
[
list(z)
for z in zip(edu_type,edu_num)
],
center=["40%", "50%"],
)
.set_global_opts(
title_opts=opts.TitleOpts(title="Python学历要求"),
legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
)
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)
c.load_javascript()
c.render_notebook()
df['城市'] = df['城市'].str.split('·').str[0]
city_type = df['城市'].value_counts().index.to_list()
city_num = df['城市'].value_counts().to_list()
c = (
Pie()
.add(
"",
[
list(z)
for z in zip(city_type,city_num)
],
center=["40%", "50%"],
)
.set_global_opts(
title_opts=opts.TitleOpts(title="Python招聘城市分布"),
legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
)
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)
c.render_notebook()
def LowMoney(i):
if '万' in i:
low = i.split('-')[0]
if '千' in low:
low_num = low.replace('千', '')
low_money = int(float(low_num) * 1000)
else:
low_money = int(float(low) * 10000)
else:
low = i.split('-')[0]
if '元/天' in low:
low_num = low.replace('元/天', '')
low_money = int(low_num) * 30
else:
low_money = int(float(low) * 1000)
return low_money
df['最低薪资'] = df['薪资'].apply(LowMoney)
def MaxMoney(j):
Max = j.split('-')[-1].split('·')[0]
if '万' in Max and '万/年' not in Max:
max_num = int(float(Max.replace('万', '')) * 10000)
elif '千' in Max:
max_num = int(float(Max.replace('千', '')) * 1000)
elif '元/天' in Max:
max_num = int(Max.replace('元/天', '')) * 30
else:
max_num = int((int(Max.replace('万/年', '')) * 10000) / 12)
return max_num
df['最高薪资'] = df['薪资'].apply(MaxMoney)
def tranform_price(x):
if x <= 5000.0:
return '0~5000元'
elif x <= 8000.0:
return '5001~8000元'
elif x <= 15000.0:
return '8001~15000元'
elif x <= 25000.0:
return '15001~25000元'
else:
return '25000以上'
df['最低薪资分级'] = df['最低薪资'].apply(lambda x:tranform_price(x))
price_1 = df['最低薪资分级'].value_counts()
datas_pair_1 = [(i, int(j)) for i, j in zip(price_1.index, price_1.values)]
df['最高薪资分级'] = df['最高薪资'].apply(lambda x:tranform_price(x))
price_2 = df['最高薪资分级'].value_counts()
datas_pair_2 = [(i, int(j)) for i, j in zip(price_2.index, price_2.values)]
pie1 = (
Pie(init_opts=opts.InitOpts(theme='dark',width='1000px',height='600px'))
.add('', datas_pair_1, radius=['35%', '60%'])
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%"))
.set_global_opts(
title_opts=opts.TitleOpts(
title="Python工作薪资\n\n最低薪资区间",
pos_left='center',
pos_top='center',
title_textstyle_opts=opts.TextStyleOpts(
color='#F0F8FF',
font_size=20,
font_weight='bold'
),
)
)
.set_colors(['#EF9050', '#3B7BA9', '#6FB27C', '#FFAF34', '#D8BFD8', '#00BFFF', '#7FFFAA'])
)
pie1.render_notebook()
pie1 = (
Pie(init_opts=opts.InitOpts(theme='dark',width='1000px',height='600px'))
.add('', datas_pair_2, radius=['35%', '60%'])
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%"))
.set_global_opts(
title_opts=opts.TitleOpts(
title="Python工作薪资\n\n最高薪资区间",
pos_left='center',
pos_top='center',
title_textstyle_opts=opts.TextStyleOpts(
color='#F0F8FF',
font_size=20,
font_weight='bold'
),
)
)
.set_colors(['#EF9050', '#3B7BA9', '#6FB27C', '#FFAF34', '#D8BFD8', '#00BFFF', '#7FFFAA'])
)
pie1.render_notebook()
exp_type = df['经验'].value_counts().index.to_list()
exp_num = df['经验'].value_counts().to_list()
c = (
Pie()
.add(
"",
[
list(z)
for z in zip(exp_type,exp_num)
],
center=["40%", "50%"],
)
.set_global_opts(
title_opts=opts.TitleOpts(title="Python招聘经验要求"),
legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
)
.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)
c.render_notebook()
# 按城市分组并计算平均薪资
avg_salary = df.groupby('城市')['最低薪资'].mean()
CityType = avg_salary.index.tolist()
CityNum = [int(a) for a in avg_salary.values.tolist()]
avg_salary_1 = df.groupby('城市')['最高薪资'].mean()
CityType_1 = avg_salary_1.index.tolist()
CityNum_1 = [int(a) for a in avg_salary_1.values.tolist()]
from pyecharts.charts import Bar
# 创建柱状图实例
c = (
Bar()
.add_xaxis(CityType)
.add_yaxis("", CityNum)
.set_global_opts(
title_opts=opts.TitleOpts(title="各大城市Python低平均薪资"),
visualmap_opts=opts.VisualMapOpts(
dimension=1,
pos_right="5%",
max_=30,
is_inverse=True,
),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)) # 设置X轴标签旋转角度为45度
)
.set_series_opts(
label_opts=opts.LabelOpts(is_show=False),
markline_opts=opts.MarkLineOpts(
data=[
opts.MarkLineItem(type_="min", name="最小值"),
opts.MarkLineItem(type_="max", name="最大值"),
opts.MarkLineItem(type_="average", name="平均值"),
]
),
)
)
c.render_notebook()
# 创建柱状图实例
c = (
Bar()
.add_xaxis(CityType_1)
.add_yaxis("", CityNum_1)
.set_global_opts(
title_opts=opts.TitleOpts(title="各大城市Python高平均薪资"),
visualmap_opts=opts.VisualMapOpts(
dimension=1,
pos_right="5%",
max_=30,
is_inverse=True,
),
xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=45)) # 设置X轴标签旋转角度为45度
)
.set_series_opts(
label_opts=opts.LabelOpts(is_show=False),
markline_opts=opts.MarkLineOpts(
data=[
opts.MarkLineItem(type_="min", name="最小值"),
opts.MarkLineItem(type_="max", name="最大值"),
opts.MarkLineItem(type_="average", name="平均值"),
]
),
)
)
c.render_notebook()
### 结论:
1. 学历要求基本大专以上
2. 薪资待遇: 8000-25000 左右
3. 北上广 薪资偏高一些
### 如何简单实现可视化分析
1. 通过爬虫采集完整的数据内容 --> 表格 / 数据库
2. 读取文件内容
3. 统计每个类目的数据情况
4. 通过可视化模块: <使用官方文档提供代码模板去实现>
import pandas as pd
# 读取数据
df = pd.read_csv('data.csv')
# 显示前五行数据
df.head()
c_type = df['公司性质'].value_counts().index.to_list() # 统计数据类目
c_num = df['公司性质'].value_counts().to_list() # 统计数据个数
c_type
from pyecharts.charts import Bar # 导入pyecharts里面柱状图
from pyecharts.faker import Faker # 导入随机生成数据
from pyecharts.globals import ThemeType # 主题设置
c = (
Bar({"theme": ThemeType.MACARONS}) # 主题设置
.add_xaxis(c_type) # x轴数据
.add_yaxis("", c_num) # Y轴数据
.set_global_opts(
# 标题显示
title_opts={"text": "Python招聘企业公司性质分布", "subtext": "民营', '已上市', '外资（非欧美）', '合资', '国企', '外资（欧美）', '事业单位'"}
)
# 保存html文件
# .render("bar_base_dict_config.html")
)
# print(Faker.choose()) # ['小米', '三星', '华为', '苹果', '魅族', 'VIVO', 'OPPO'] 数据类目
# print(Faker.values()) # [38, 54, 20, 85, 71, 22, 38] 数据个数
c.render_notebook() # 直接显示在jupyter上面