当前位置: 萬仟网 > IT编程>网页制作>HTML > (1)爬虫笔记备份

(1)爬虫笔记备份

2020年07月07日  | 萬仟网IT编程  | 我要评论
'''
第一天
import requests
from urllib.request import urlopen
url = 'http://quote.eastmoney.com/us/BIDU.html?from=BaiduAladdin'
response = urlopen(url)
info = response.read()
print(info.decode())
print(response.info())
'''



'''
动态UA

pip install fake_useragent
from fake_useragent import UserAgent
ua=UserAgent()
print(ua.chrome)

from urllib.request import urlopen
from urllib.request import Request
from random import choice
url = 'http://quote.eastmoney.com/us/BIDU.html?from=BaiduAladdin'
user_agents=['Mozilla/5.0(Windows;U;WindowsNT6.1;en-us)AppleWebKit/534.50(KHTML,likeGecko)Version/5.1Safari/534.50',
             'Mozilla/5.0(Macintosh;IntelMacOSX10.6;rv:2.0.1)Gecko/20100101Firefox/4.0.1',
             'Opera/9.80(Macintosh;IntelMacOSX10.6.8;U;en)Presto/2.8.131Version/11.11']
print(choice(user_agents))
headers={
    'User-Agent':choice(user_agents)
}
request=Request(url,headers=headers)
response=urlopen(request)
info=response.read()
print(info.decode())
'''





'''
搜索中文转码1

from urllib.request import urlopen
from urllib.request import Request
from urllib.parse import quote
print(quote('历史'))
url = 'https://www.baidu.com/s?wd={}'.format(quote('历史'))
headers={
    'User-Agent':'Mozilla/5.0(Windows;U;WindowsNT6.1;en-us)AppleWebKit/534.50(KHTML,likeGecko)Version/5.1Safari/534.50'
}
print(url)
request = Request(url,headers=headers)
response= urlopen(request)
print(response.read().decode())
'''

'''
搜索中文转码2

from urllib.request import urlopen
from urllib.request import Request
from urllib.parse import urlencode
arg={
'wd':'历史',
'ie':'utf-8'
}
print(urlencode(arg))
url = 'https://www.baidu.com/s?{}'.format(urlencode(arg))
headers={
    'User-Agent':'Mozilla/5.0(Windows;U;WindowsNT6.1;en-us)AppleWebKit/534.50(KHTML,likeGecko)Version/5.1Safari/534.50'
}
print(url)
request = Request(url,headers=headers)
response= urlopen(request)
print(response.read().decode())

'''


'''
爬贴吧

‘’‘
'''
from urllib.request import urlopen
from urllib.request import Request
from urllib.parse import urlencode
from random import choice
def  get_html(url):
    user_agents = ['Mozilla/5.0(Windows;U;WindowsNT6.1;en-us)AppleWebKit/534.50(KHTML,likeGecko)Version/5.1Safari/534.50',
             'Mozilla/5.0(Macintosh;IntelMacOSX10.6;rv:2.0.1)Gecko/20100101Firefox/4.0.1',
             'Opera/9.80(Macintosh;IntelMacOSX10.6.8;U;en)Presto/2.8.131Version/11.11']
    #print(choice(user_agents))
    headers = {
        'User-Agent': choice(user_agents)
    }
    request=Request(url,headers=headers)
    response=urlopen(request)
    return response.read()

def  save_html(filename,html_bytes):
    with open(filename,'wb') as f:
        f.write(html_bytes)


def main():
    content=input('download')
    num = input('num')
    base_url='https://tieba.baidu.com/f?ie=utf-8&{}'
    for pn in range(int(num)):
        args={
            'pn':pn*50,
            'kw':content
        }
        args=urlencode(args)

        print(base_url.format(args))
        #url=base_url.format(args)
        html_bytes = get_html(base_url.format(args))
        filename = '第'+str(pn+1)+'页.html'
        print('正在下载'+filename)
        save_html(filename,html_bytes)

if __name__ == '__main__':
    main()


本文地址:https://blog.csdn.net/qq_42830971/article/details/107154486

如对本文有疑问, 点击进行留言回复!!

相关文章:

验证码:
Copyright © 2017-2020  萬仟网 保留所有权利. 粤ICP备17035492号-1
站长QQ:2386932994 | 联系邮箱:2386932994@qq.com