|
|
|
@ -6,6 +6,7 @@ url = "https://top.chinaz.com/gongsi/index_zhuce.html"
|
|
|
|
headers = {
|
|
|
|
headers = {
|
|
|
|
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"
|
|
|
|
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#requests爬取网页内容
|
|
|
|
# 使用reqeusts模快发起 GET 请求
|
|
|
|
# 使用reqeusts模快发起 GET 请求
|
|
|
|
response = requests.get(url, headers=headers)
|
|
|
|
response = requests.get(url, headers=headers)
|
|
|
|
# 获取请求的返回结果
|
|
|
|
# 获取请求的返回结果
|
|
|
|
@ -30,7 +31,7 @@ for page in range(17):
|
|
|
|
capital= re.findall('注册资本：</span>(.*?)</p>', html)
|
|
|
|
capital= re.findall('注册资本：</span>(.*?)</p>', html)
|
|
|
|
# 合并列表
|
|
|
|
# 合并列表
|
|
|
|
pageOne = list(zip(company,debt ))
|
|
|
|
pageOne = list(zip(company,debt ))
|
|
|
|
message.extend(pageOne)#将列表放入message里
|
|
|
|
message.extend(pageOne) #将列表放入message里
|
|
|
|
import csv
|
|
|
|
import csv
|
|
|
|
with open("content.csv", "w") as f:
|
|
|
|
with open("content.csv", "w") as f:
|
|
|
|
w = csv.writer(f)
|
|
|
|
w = csv.writer(f)
|
|
|
|
@ -58,6 +59,7 @@ for i in range(len(df3)):
|
|
|
|
a=str(a)
|
|
|
|
a=str(a)
|
|
|
|
df3.remove(df3[0])
|
|
|
|
df3.remove(df3[0])
|
|
|
|
df3.append(a)
|
|
|
|
df3.append(a)
|
|
|
|
|
|
|
|
# 绘制条形图（饼图字迹会重合，所以不用饼图）
|
|
|
|
import matplotlib.pyplot as plt
|
|
|
|
import matplotlib.pyplot as plt
|
|
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']# 用黑体显示中文
|
|
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']# 用黑体显示中文
|
|
|
|
plt.rcParams['axes.unicode_minus'] = False # （解决坐标轴负数的负号显示问题）
|
|
|
|
plt.rcParams['axes.unicode_minus'] = False # （解决坐标轴负数的负号显示问题）
|
|
|
|
|
