Python – 网络爬虫
流程:
1. 连接链接获取页面内容(html文件);
2. 过滤获取需要信息(正则) [可能重复步骤1,2] ;
3. 存储文件到本地。
一)网络连接获取页面内容
import urllib.request as request
import urllib.error as error
import requests
headers = {
'Connection':'keep-alive',
'Accept-Language':'zh-CN,zh;q=0.9',
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
}
def getHtml(url):
try:
req = request.Request(url)
webpage = request.urlopen(req)
html = webpage.read()
return html
except error.URLError as e:
print(str(e.code) + '\t' + e.reason)
return None
def getXMLText(url):
try:
response = requests.get(url)
response.raise_for_status()
response.encoding = "utf-8"
return response.text
except:
return None
def getHtmlWithHead(url):
req = request.Request(url, headers)
webpage = request.urlopen(req)
html = webpage.read()
return html
def main():
url = input('输入网址: ')
print(getHtml(url))
print(getXMLText(url))
if __name__ == '__main__':
main()
python用于爬虫的库: urllib, requests
urllib.request 用于打开和读取URL, (request.urlopen)
urllib.error 用于处理前面request引起的异常, (:403 Forbidden)
urllib.parse 用于解析URL,
urlopen(url, data=None, timeout=<object object at 0x000001D4652FE140>, *, cafile=None, capath=None, cadefault=False, context=None)。
二)过滤、筛选、替换
1. from bs4 import BeautifulSoup as bs:
soup = bs(html, 'html.parser')
info = soup.find_all('div', attrs={'class' : 'add'})
info = soup.select('p')
2. import re
title = re.compile(r'<h2>(.*?)</h2>').search(str(info))
3. str 字符操作
author = str(info).replace('<p>','').replace('</p>','').rstrip()
三)本地存储
import os
import time
dir = 'D:\\Python\\Data\\'
path = 'D:\\Python\\Data\\text.txt'
1. create dir
isExists = os.path.exists(dir)
if not isExists:
os.mkdir(path)
2. write: 'w','wb'
file = open(path,'w',encoding='utf-8')
file.write('content')
file.close()
3. read: 'r','rb'
file = open(path, 'rb')