爬虫学习（四）——post请求爬取

百度翻译爬取数据

import urllib.request
import urllib.parse
post_url = "https://fanyi.baidu.com/sug"
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"}
word= input( "请输入要翻译的内容:" )
data = {"kw":word}

# 对表单数据进行处理时，先转换成为字符串，在转换成为字节
# 只转化成为字符串形式 
data1 = urllib.parse.urlencode(data)
print(data1)
# 输出结果
# word=%E5%AE%9D%E8%B4%9D 字符串格式

# 转换成为字节格式
data = urllib.parse.urlencode(data).encode("utf8")
print(data)
# 显示结果：
# b'word=%E5%AE%9D%E8%B4%9D' 字节格式

request = urllib.request.Request(post_url,headers=headers)
response = urllib.request.urlopen(request,data = data)
print(response.read().decode("utf8"))

百度翻译爬取数据

import urllib.request
import urllib.parse

apiurl = "https://fanyi.baidu.com/v2transapi"

在爬取目标网站时，先找准目标网站的接口，和需要传递的数据

data = {
   'from': 'en',
   'to': 'zh',
   'query': 'baby',
   'transtype': 'realtime',
   'simple_means_flag': '3',
   'sign': '814534.560887',
   'token': '8b44713bb18ae29ba380245d18270565',
}

data1= urllib.parse.urlencode( data ).encode( "utf8" )

#post请求重点是请求头信息要详细，关键的属性不能省

headers = {
   #'Accept': '*/*',
   #'Accept-Encoding': 'gzip, deflate, br',
   #'Accept-Language': 'zh-CN,zh;q=0.9',
   #'Connection': 'keep-alive',
   #'Content-Length': '121',
   #'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
   'Cookie': 'PSTM=1528269920; BIDUPSID=7EE884F5F31114F0BCDC2588805B747F; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; to_lang_often=%5B%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%2C%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%5D; from_lang_often=%5B%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%2C%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%5D; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BAIDUID=C15EE352EEB61222BDA4C2F95822E5EF:SL=0:NR=10:FG=1; pgv_pvi=4516305920; delPer=0; H_PS_PSSID=1436_21101_28206_28131_26350_28139; PSINO=2; locale=zh; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1546425466,1546425533,1546425602,1546484054; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1546487219',
   'Host': 'fanyi.baidu.com',
   'Origin': 'https://fanyi.baidu.com',
   'Referer': 'https://fanyi.baidu.com/',
   'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',
   'X-Requested-With': 'XMLHttpRequest',

}

request = urllib.request.Request( url=apiurl, headers=headers )
response = urllib.request.urlopen( request, data=data1 )
print(response.read().decode( "utf8" ) )

ajax的post请求
爬取KFC的餐厅地址

import urllib.request
import urllib.parse
url = "http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword"
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"}
# 表单输入地址信息
keyword =input("请输入需要查询的城市")
#请求网页需要进行传递的参数
data = {
    "cname":"",
    "pid": "",
    "keyword": keyword,
    "pageIndex": "1",
    "pageSize": "10",
}
# 解析参数，编程字节格式
data = urllib.parse.urlencode(data).encode("utf8")
# 构建请求头信息
request = urllib.request.Request(url,headers = headers)
# 发送请求，获取相应数据,重点是附带参数的post请求。
response = urllib.request.urlopen(request,data=data)
# 读取响应信息
print(response.read().decode("utf8"))