Python爬取研招网数据

一、爬虫定制部分

# 导入相关的包
import requests
import lxml.html
import chardet
import pandas as pd
import numpy as np


#请求头获取页面
def get_page(url,headers):
    try:
        r=requests.get(url, headers=headers)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except Exception as e:
        print(e)


# 定制请求头
headers = {
    
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'}

二、爬取并解析网页

# 爬取的网址url
url = "https://yz.chsi.com.cn/kyzx/fsfsx34/201703/20170306/1589083359.html"
page = get_page(url,headers)
selector = lxml.html.fromstring(page)


# 利用xpath进行数据的爬取，数据保存到列表中
sample = []
for i in range(2,13):
    subject = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td/p/text()'.format(i))
    sample.append([subject[0],subject[1],subject[-1]])
    

三、保存数据

# 将数据用DataFrame表示并输出到csv
df = pd.DataFrame(data=sample,dtype='object',columns=['学科代码','名称', '总分'])
df.to_csv('C:/Users/David/Desktop/东南大学2017年初试学术学位成绩.csv',header=True,index=False,encoding='utf-8')

四、绘图分析

'''
    绘图部分
'''
import matplotlib
import matplotlib.pyplot as plt
import numpy as np


labels = df['名称']
grade_2019 = df['2019年总分']
grade_2018 = df['2018年总分']
grade_2017 = df['2017年总分']
grade_2016 = df['2016年总分']


x = np.arange(len(labels))  # the label locations
width = 0.15  # the width of the bars

type(x-width/2)

fig, ax = plt.subplots()
rects1 = ax.bar(x - width/2, grade_2016, width, label='2016')
rects2 = ax.bar(x + width/2, grade_2017, width, label='2017')
rects3 = ax.bar(x + width/2 +width, grade_2018, width, label='2018')
rects4 = ax.bar(x + width/2 +width + width, grade_2019, width, label='2019')

# Add some text for labels, title and custom x-axis tick labels, etc.
ax.set_ylabel('分数')
ax.set_title('东南大学2016-2019年初试学术学位成绩')
ax.set_xticks(x)
ax.set_xticklabels(labels)
ax.legend()
plt.show()

五、全代码

#!/usr/bin/env python
# coding: utf-8

# 导入相关的包
import requests
import lxml.html
import chardet
import pandas as pd
import numpy as np


#请求头获取页面
def get_page(url,headers):
    try:
        r=requests.get(url, headers=headers)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except Exception as e:
        print(e)


# 定制请求头
headers = {
    
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'}



#########################################################################################
# 爬取的网址url
url = "https://yz.chsi.com.cn/kyzx/fsfsx34/201703/20170306/1589083359.html"
page = get_page(url,headers)
selector = lxml.html.fromstring(page)


# 利用xpath进行数据的爬取，数据保存到列表中
sample = []
for i in range(2,13):
    subject = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td/p/text()'.format(i))
    sample.append([subject[0],subject[1],subject[-1]])
    
    
# 将数据用DataFrame表示并输出到csv
df = pd.DataFrame(data=sample,dtype='object',columns=['学科代码','名称', '总分'])
df.to_csv('C:/Users/David/Desktop/东南大学2016年初试学术学位成绩.csv',header=True,index=False,encoding='utf8')
#################################################################################

# 爬取的网址url
url = "https://yz.chsi.com.cn/kyzx/fsfsx34/201703/20170306/1589085174.html"
page = get_page(url,headers)
selector = lxml.html.fromstring(page)


# 利用xpath进行数据的爬取，数据保存到列表中
sample = []
for i in range(2,13):
    id = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td[1]/span/text()'.format(i))
    subject = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td[2]/text()'.format(i))
    grade = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td[7]/div/span/text()'.format(i))
    sample.append([id[0],subject[0],grade[0]])
    
    
# 将数据用DataFrame表示并输出到csv
df = pd.DataFrame(data=sample,dtype='object',columns=['学科代码','名称', '总分'])
df.to_csv('C:/Users/David/Desktop/东南大学2017年初试学术学位成绩.csv',header=True,index=False,encoding='utf-8')
#############################################################################################
# 爬取的网址url
url = "https://yz.chsi.com.cn/kyzx/fsfsx34/201803/20180305/1664240306.html"
page = get_page(url,headers)
selector = lxml.html.fromstring(page)


# 利用xpath进行数据的爬取，数据保存到列表中
sample = []
for i in range(2,13):
    id = selector.xpath('//*[@id="article_dnull"]/center[1]/table/tbody/tr[{}]/td[1]/text()'.format(i))
    subject = selector.xpath('//*[@id="article_dnull"]/center[1]/table/tbody/tr[{}]/td[2]/text()'.format(i))
    grade = selector.xpath('//*[@id="article_dnull"]/center[1]/table/tbody/tr[{}]/td[7]/text()'.format(i))
    sample.append([id[0],subject[0],grade[0]])
    
    
# 将数据用DataFrame表示并输出到csv
df = pd.DataFrame(data=sample,dtype='object',columns=['学科代码','名称', '总分'])
df.to_csv('C:/Users/David/Desktop/东南大学2018年初试学术学位成绩.csv',header=True,index=False,encoding='utf-8')

##################################################################################################
# 爬取的网址url
url = "https://yz.chsi.com.cn/kyzx/fsfsx34/201903/20190306/1770746646.html"
page = get_page(url,headers)
selector = lxml.html.fromstring(page)


# 利用xpath进行数据的爬取，数据保存到列表中
sample = []
for i in range(2,13):
    id = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td[1]/text()'.format(i))
    subject = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td[2]/text()'.format(i))
    grade = selector.xpath('//*[@id="article_dnull"]/table[1]/tbody/tr[{}]/td[7]/text()'.format(i))
    sample.append([id[0],subject[0],grade[0]])
    
    
# 将数据用DataFrame表示并输出到csv
df = pd.DataFrame(data=sample,dtype='object',columns=['学科代码','名称', '总分'])
df.to_csv('C:/Users/David/Desktop/东南大学2019年初试学术学位成绩.csv',header=True,index=False,encoding='utf-8')

#############################################################################################3

'''
        绘图准备部分
'''
import pandas as pd
df_2019 = pd.read_csv("C:/Users/David/Desktop/东南大学2019年初试学术学位成绩.csv")
df_2018 = pd.read_csv("C:/Users/David/Desktop/东南大学2018年初试学术学位成绩.csv")
df_2017 = pd.read_csv("C:/Users/David/Desktop/东南大学2017年初试学术学位成绩.csv")
df_2016 = pd.read_csv("C:/Users/David/Desktop/东南大学2016年初试学术学位成绩.csv")	

df_2019['学科代码']

df = pd.DataFrame(data=df_2019)
df = df.rename(columns = {
    
    "总分": "2019年总分"})
df['2018年总分'] = df_2018['总分']
df['2017年总分'] = df_2017['总分']
df['2016年总分'] = df_2016['总分']

df.to_csv('C:/Users/David/Desktop/东南大学2016-2019年初试学术学位成绩.csv',header=True,index=False,encoding='utf-8')


############################################
'''
    绘图部分
'''
import matplotlib
import matplotlib.pyplot as plt
import numpy as np


labels = df['名称']
grade_2019 = df['2019年总分']
grade_2018 = df['2018年总分']
grade_2017 = df['2017年总分']
grade_2016 = df['2016年总分']


x = np.arange(len(labels))  # the label locations
width = 0.15  # the width of the bars

type(x-width/2)

fig, ax = plt.subplots()
rects1 = ax.bar(x - width/2, grade_2016, width, label='2016')
rects2 = ax.bar(x + width/2, grade_2017, width, label='2017')
rects3 = ax.bar(x + width/2 +width, grade_2018, width, label='2018')
rects4 = ax.bar(x + width/2 +width + width, grade_2019, width, label='2019')

# Add some text for labels, title and custom x-axis tick labels, etc.
ax.set_ylabel('分数')
ax.set_title('东南大学2016-2019年初试学术学位成绩')
ax.set_xticks(x)
ax.set_xticklabels(labels)
ax.legend()
plt.show()