链家房源信息爬取
爬取10页
import requests
import re
import time
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'}
data=pd.DataFrame()
import random
for i in range(1,11):#爬取10页
print('正在爬取第%d页'%i)
baseurl='https://bj.lianjia.com/zufang/pg'
url=baseurl+str(i)+'/#contentList'
response = requests.get(url, headers=header)
html=response.text
nameregex=re.compile('alt="(.*?)"\n')
name = nameregex.findall(html) #找出所有小区名字
arearegex=re.compile('([0-9]+)㎡\n')
area = arearegex.findall(html) #找出面积
priceregex=re.compile('<em>([0-9.]+)</em> 元/月')
price = priceregex.findall(html) #找出价格
datalist=[]
for i in range(len(name)):
datalist.append([name[i],float(area[i]),float(price[i])])
df=pd.DataFrame(datalist)
data=pd.concat([data,df])
time.sleep(random.randint(6,7))
print('爬取完毕')
data.columns=['name','area','price']
data.set_index('name').sort_values('area')
有道翻译 post请求
界面形式
#界面形式
content=input('请输入内容:')
import requests
url='http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null'
formdata = {'i':content,
'from':'AUTO',
'to':'AUTO',
'smartresult':'dict',
'client': 'fanyideskweb',
'salt':'1541165120374',
'sign':'5bbeca852044319291d932d4bfe92564',
'doctype':'json',
'version':'2.1',
'keyfrom':'fanyi.web',
'action':'FY_BY_REALTIME',
'typoResult':'false'
}
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'}
response = requests.post(url, data=formdata,headers=header)
print(response.json()['translateResult'][0][0]['tgt'])
翻译多个内容
#翻译多个内容
import requests
import time
url='http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null'
contents=['中国','美国','英国','法国']
for content in contents:
formdata = {'i':content,
'from':'AUTO',
'to':'AUTO',
'smartresult':'dict',
'client': 'fanyideskweb',
'salt':'1541165120374',
'sign':'5bbeca852044319291d932d4bfe92564',
'doctype':'json',
'version':'2.1',
'keyfrom':'fanyi.web',
'action':'FY_BY_REALTIME',
'typoResult':'false'
}
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'}
response = requests.post(url, data=formdata,headers=header)
print(response.json()['translateResult'][0][0]['tgt'])
time.sleep(5)