从各个城市的律师协会去爬取的律师的招聘信息,可是邮箱在招聘简介里面,所有需要写个脚本去提取邮箱
import pandas as pd
import re
regex = r"([-_a-zA-Z0-9.]{0,64}@([-w]{1,63}.)*[-a-zA-Z0-9-.]{1,63})"
regex_1 = r"([a-zA-Z0-9_.+-]+@[a-pr-zA-PRZ0-9-]+.[a-zA-Z0-9-.]+)"
df = pd.read_excel('11-28+深圳律师.xls')
# for d in df['福利待遇及联系信息(必填)']:
# emails = re.findall(regex, d)
# if emails:
# print(emails[0])
# else:
# print('wu')
for i in range(len(df['福利待遇及联系信息(必填)'])):
email = re.findall(regex, df['福利待遇及联系信息(必填)'][i])
email_1 = re.findall(regex_1, df['福利待遇及联系信息(必填)'][i])
print(email,email_1)
if email_1:
df['HR邮箱(必填)'][i] = email_1[0]
elif email:
df['HR邮箱(必填)'][i] = email[0][0]
else:
print(i)
break
df.to_excel('shenzhen.xls')