当前位置 博文首页 > 主打Python的博客：用python爬取基金网信息数据，保存到表格，并
上次 2021-07-07写的用python爬取腾讯招聘网岗位信息保存到表格，并做成简单可视化。
有的人留言问我：
可以作为模板么？
我的回答：
可以，可以拿做模板使用
今天我带大家再来使用一下这个模板
开发环境：
windows10
python3.6
开发工具：
pycharm
库：
matplotlib、numpy、lxml
1.start_url = ‘http://fund.eastmoney.com/fund.html’
2.使用ua大列表，进行ua的替换
3.获取页面源码，然后解析
4.进行xpath语法提取相应的数据
def __init__(self):
# 起始的请求地址----初始化
self.start_url = 'http://fund.eastmoney.com/fund.html'
def parse_start_url(self):
"""
发送请求，获取响应
:return:
"""
# 请求头
headers = {
# 通过随机模块提供的随机拿取数据方法
'User-Agent': random.choice(USER_AGENT_LIST)
}
# 发送请求，获取响应字节数据
response = session.get(self.start_url, headers=headers).content
"""序列化对象，将字节内容数据，经过转换，变成可进行xpath操作的对象"""
response = etree.HTML(response)
"""调用提取第二份响应数据"""
self.parse_response_data(response)
def parse_response_data(self, response):
"""
解析response响应数据，提取
:return:
"""
# 股票名称
name_list_1 = response.xpath('//tbody/tr/td[5]/nobr/a[1]/text()')
# 昨日单位净值
num_1_list_data_1 = response.xpath('//tbody/tr/td[6]/text()')
# 昨日累计净值
num_2_list_data_1 = response.xpath('//tbody/tr/td[7]/text()')
# 遍历解析3个列表数据
for a, b, c in zip(name_list, num_1_list, num_2_list):
# 构造保存的excel字典数据
dict_data = {
# 会根据该字典的key值创建工作簿的sheet名
'股票数据': [a, b, c]
}
"""调用解析保存excel表格方法"""
self.parse_save_excel(dict_data)
def parse_img_four_func(self, index_list, name_list, num_1_list, num_2_list):
"""
解析生成四张分析图
:param index_list: 随机数据的下标
:param name_list: 股票名称列表
:param num_1_list: 昨日单位净值列表
:param num_2_list: 昨日累计净值列表
:return:
"""
title_list = [] # 名称
qy_num_1 = [] # 单位净值
qy_num_2 = [] # 累计净值
for index_num in index_list:
# 企业名称列表
title_list.append(name_list[index_num])
# 昨日单位净值列表
qy_num_1.append(num_1_list[index_num])
# 昨日累计净值列表
qy_num_2.append(num_2_list[index_num])
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# plot中参数的含义分别是横轴值，纵轴值，线的形状，颜色，透明度,线的宽度和标签
plt.plot(title_list, qy_num_2, 'ro-', color='#4169E1', alpha=0.8, linewidth=1, label='累计净值')
plt.plot(title_list, qy_num_1, 'ro-', color='#69e141', alpha=0.8, linewidth=1, label='单位净值')
# 显示标签，如果不加这句，即使在plot中加了label='一些数字'的参数，最终还是不会显示标签
plt.legend(loc="upper right")
plt.xticks(rotation=270)
plt.xlabel('地点数量')
plt.ylabel('工作属性数量')
plt.savefig('根据净值生成折线图.png')
plt.show()
addr_dict_key = title_list
addr_dict_value = qy_num_1
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
plt.rcParams['axes.unicode_minus'] = False
plt.pie(addr_dict_value, labels=addr_dict_key, autopct='%1.1f%%')
plt.title(f'单位净值对比')
plt.savefig(f'单位净值对比-饼图')
plt.show()
# 这两行代码解决 plt 中文显示的问题
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 输入岗位地址和岗位属性数据
production = title_list
tem = qy_num_2
colors = np.random.rand(len(tem)) # 颜色数组
plt.scatter(tem, production, s=200, c=colors) # 画散点图，大小为 200
plt.xlabel('数量') # 横坐标轴标题
plt.xticks(rotation=270)
plt.ylabel('名称') # 纵坐标轴标题
plt.savefig(f'净值散点图.png')
plt.show()
import matplotlib;matplotlib.use('TkAgg')
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
zhfont1 = matplotlib.font_manager.FontProperties(fname='C:\Windows\Fonts\simsun.ttc')
name_list = title_list
num_list = [float(i) for i in qy_num_1] # 单位净值
width = 0.5 # 柱子的宽度
index = np.arange(len(name_list))
plt.bar(index, num_list, width, color='steelblue', tick_label=name_list, label='单位净值')
plt.bar(index + width, qy_num_2, width, color='red', hatch='\\', label='累计净值')
plt.legend(['单位净值', '累计净值'], prop=zhfont1, labelspacing=1)
for a, b in zip(index, num_list): # 柱子上的数字显示
plt.text(a, b, '%.2f' % b, ha='center', va='bottom', fontsize=7)
plt.xticks(rotation=270)
plt.title('净值柱状图')
plt.ylabel('率')
plt.legend()
plt.savefig(f'净值-柱状图', bbox_inches='tight')
plt.show()
# !/usr/bin/nev python
# -*-coding:utf8-*-
"""ua大列表"""
USER_AGENT_LIST = [
'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3451.0 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:57.0) Gecko/20100101 Firefox/57.0',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.71 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.2999.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.70 Safari/537.36',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.4; en-US; rv:1.9.2.2) Gecko/20100316 Firefox/3.6.2',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.155 Safari/537.36 OPR/31.0.1889.174',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.1.4322; MS-RTC LM 8; InfoPath.2; Tablet PC 2.0)',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36 OPR/55.0.2994.61',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.814.0 Safari/535.1',
'Mozilla/5.0 (Macintosh; U; PPC Mac OS X; ja-jp) AppleWebKit/418.9.1 (KHTML, like Gecko) Safari/419.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0; Touch; MASMJS)',
'Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.21 (KHTML, like Gecko) Chrome/19.0.1041.0 Safari/535.21',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3451.0 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:57.0) Gecko/20100101 Firefox/57.0',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.71 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.2999.0 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.70 Safari/537.36',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.4; en-US; rv:1.9.2.2) Gecko/20100316 Firefox/3.6.2',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.155 Safari/537.36 OPR/31.0.1889.174',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.1.4322; MS-RTC LM 8; InfoPath.2; Tablet PC 2.0)',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
