红牛分公司数据part02

简单爬取红牛分公司基本数据part02

此教材利用requests、pandas、bs4三个模块。

代码实现如下：

方式一：直接在终端打印

import requests
import pandas
from bs4 import BeautifulSoup

url=requests.get('http://www.redbull.com.cn/about/branch')

soup = BeautifulSoup(url.text,'lxml')

# title_list = soup.find_all(name='h2')
# for title in title_list:
#     print(title.text)

# addr_list = soup.find_all(name='p',class_='mapIco')
# for addr in addr_list:
#     print(addr.text)

# email_list = soup.find_all(name='p',class_='mailIco')
# for email in email_list:
#     print(email.text)

# phone_list = soup.find_all(name='h2')
# for phone in phone_list:
#     print(phone.text)


# 列表生成式
title_list = [title.text for title in soup.find_all(name='h2')]
# print(title_list)
addr_list = [addr.text for addr in soup.find_all(name='p',class_='mapIco')]
# print(addr_list)
email_list = [email.text for email in soup.find_all(name='p',class_='mailIco')]
# print(email_list)
phone_list = [phone.text for phone in soup.find_all(name='p',class_='telIco')]
# print(phone_list)

# for i in range(40):
#     print('''
# 公司名称:%s
# 公司地址:%s
# 公司邮箱:%s
# 公司电话:%s
#     '''%(title_list[i],addr_list[i],email_list[i],phone_list[i]))

方式二：保存到Excel表格中

import requests
import pandas
from bs4 import BeautifulSoup

url=requests.get('http://www.redbull.com.cn/about/branch')

soup = BeautifulSoup(url.text,'lxml')

# title_list = soup.find_all(name='h2')
# for title in title_list:
#     print(title.text)

# addr_list = soup.find_all(name='p',class_='mapIco')
# for addr in addr_list:
#     print(addr.text)

# email_list = soup.find_all(name='p',class_='mailIco')
# for email in email_list:
#     print(email.text)

# phone_list = soup.find_all(name='h2')
# for phone in phone_list:
#     print(phone.text)


# 列表生成式
title_list = [title.text for title in soup.find_all(name='h2')]
# print(title_list)
addr_list = [addr.text for addr in soup.find_all(name='p',class_='mapIco')]
# print(addr_list)
email_list = [email.text for email in soup.find_all(name='p',class_='mailIco')]
# print(email_list)
phone_list = [phone.text for phone in soup.find_all(name='p',class_='telIco')]
# print(phone_list)

data_dict = {
    
    
"公司名称":title_list,
"公司地址":addr_list,
"公司邮箱":email_list,
"公司电话":phone_list
}
df = pandas.DataFrame(data_dict)
df.to_excel(r'data_info.xlsx')

更多精彩，后续更新！！！