python 爬取企业注册信息_【Python】利用requests和selenium爬取企业竞争公司信息

[Python] 纯文本查看 复制代码#读取公司名称

path ="C:/Users/wxx/Desktop/公司名称.xlsx" #公司名称可以放在excel表格里

df = pd.read_excel(path)

df1 = df['公司名称'].values #获取公司名称这一列的值

print(df1)

ids = []

companys = []

for key in df1[0:]:

print(key) #公司名称

url = 'https://www.qichacha.com/search?key='+key

id, company = get_id(url)

ids.append(id)

companys.append(company)

time.sleep(3.44+random.random()) #在使用requests时必须适当控制爬取速度，防止被封，或者使用代{过}{滤}理IP

print(companys)

idsshape=([i for item in ids for i in item]) #不理解这一块的内容时请查看ids的类型为二维list就知道了

print(idsshape)

messages = [] #存储公司专利信息

for i in range(len(companys)):#data.shape[0]

company = companys[i]

id = idsshape[i]

url = 'https://www.qichacha.com/company_getinfos?unique='+id + '&companyname=' + company +'&p='+ '&tab=report'

message = get_message(url)

companyname = df1[i]

txtpath = 'C:/Users/wxx/Desktop/竞品公司/'+companyname+'竞品.txt'

with open(txtpath,"w") as f:

f.write('竞争公司'+'\t\t'+'融资状态'+'\t\t'+'市值'+'\t\t'+'日期'+'\t\t'+'地点'+'\t\t'+'公司名称'+'\t\t'+'业务介绍')

for j in range(len(message)):

number = jingpin()

number.name = message[j][0]

number.status = message[j][1]

number.date = message[j][2]

number.location = message[j][3]

number.introduction = message[j][4]

number.comname = message[j][5]

if number.status == 'IPO':

url1 = 'http://so.eastmoney.com/web/s?keyword='+number.name

page = get_shizhi(url1)

print(page)

number.value = page

elif number.status == '新三板':

url1 = 'http://so.eastmoney.com/web/s?keyword='+number.name

page = get_shizhi(url1)

print(page)

number.value = page

else:

number.value = '无'

try:

with open(txtpath,"a") as f:

f.write('\n'+number.name+'\t\t'+number.status+'\t\t'+str(number.value[0])+'\t\t'+number.date+'\t\t'+number.location+'\t\t'+number.comname+'\t\t'+number.introduction)

except UnicodeEncodeError: #这里使用try是因为爬取信息中出现了txt无法解析的字符，防止中断程序，非常有用

with open(txtpath,"a") as f:

f.write('\n'+number.name+'\t\t'+number.status+'\t\t'+str(number.value[0])+'\t\t'+number.date+'\t\t'+number.location+'\t\t'+number.comname)

print(companyname+'竞品公司收集完成！')

time.sleep(2.56+random.random())