python 简单 爬虫

import urllib.request
import  urllib.error
# response=urllib.request.urlopen("http://www.baidu.com")
# print(response.read().decode('utf-8'))

import urllib.parse


# try:
#     data = bytes(urllib.parse.urlencode({"hello":"world"}),encoding="utf-8")
#     response=urllib.request.urlopen("http://httpbin.org/post",data,timeout=0.01)
#
#     print(response.read().decode("utf-8"))
# except urllib.error.URLError as e:
#     print("time out")


# try:
#     response = urllib.request.urlopen("http://httpbin.org/get",timeout=0.01)
#     print(response.read().decode("utf-8"))
# except urllib.error.URLError as e:
#     print("time out")


# response=urllib.request.urlopen("http://httpbin.org/get")
# print(response.status)

# response=urllib.request.urlopen("http://www.baidu.com")
# print(response.status)
# print(response.getheaders())
# print(response.getheader("server"))

# url = "https://douban.com"
# headers = {
#   "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36"
# }
# data = bytes(urllib.parse.urlencode({'name':'eric'}),encoding="utf-8")
# req = urllib.request.Request(url=url, data=data, headers=headers, method="post")
# response = urllib.request.urlopen(req)
# print(response.read().decode("utf-8"))

 

from bs4 import BeautifulSoup
import re
import urllib.request, urllib.error
import xlwt
import sqlite3


def main():
    basel = "https://movie.douban.com/top250?start="
    askurl(basel)
    # 1  抓取网页

    sabbath = ".\\top250.xls"
    saveData(sabbath)

    # 2  解析数据

    print("hello")


# 爬取网页

def getData(baseurl):
    datalist = []
    return datalist


# 3  保存数据
def saveData(savepath):
    print("save....")


def askurl(url):
    head={
       "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36"
     }
    request=urllib.request.Request(url,headers=head)
    html =""
    try:
        response=urllib.request.urlopen(request)
        html=response.read().decode("utf-8")
        print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        print("error")

if __name__ == '__main__':
    main()