网页爬虫python代码_Python 爬虫web网页版程序代码

一：网页结构分析

二：代码实战#! /usr/bin/env python2

# encoding=utf-8

#BeautifulSoup需要安装 MySQLdb

import sys,os,re,hashlib

import urllib

import httplib2

from lxml import etree

import MySQLdb

from BeautifulSoup import BeautifulSoup

import urllib2

import re

import time

reload(sys)

from datetime import datetime as dt,timedelta

import re

h=httplib2.Http(timeout=10)

#设置请求http头 模拟伪装 浏览器

headers={

'User-Agent':'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)'

}

#正则匹配a标签

pattern = '(.*?)'

#日志记录

log_path='./sporttery'

log_file='%s.log' % dt.now().strftime('%Y-%m-%d')

if not os.path.exists(log_path):

os.makedirs(log_path)

log=open('%s/%s' % (log_path,log_file),'w+')

#python操作mysql数据库

conn= MySQLdb.connect(

host='localhost',

port = 3306,

user='root',

passwd='root',

db ='test',

)

conn.set_character_set('utf8')

cur = conn.cursor()

cur.execute('SET NAMES utf8;')

cur.execute('SET CHARACTER SET utf8;')

cur.execute('SET character_set_connection=utf8;')

cur.close()

#获取请求链接内容 失败再次执行

def download(url):

fails = 0

while True:

if fails>5:return None

try:

res,content = h.request(url,'GET',headers=headers)

return content.decode('utf-8','ignore')

except:

print(u'打开链接失败'+url)

fails +=1

#字符串截取方法

def GetMiddleStr(content,startStr,endStr):

startIndex = content.index(startStr)

if startIndex>=0:

startIndex += len(startStr)

endIndex = content.index(endStr)

return content[startIndex:endIndex]

def get_ul(data):

mystring=GetMiddleStr(data,'','')

return mystring

def test_sporttery(i):

url='http://www.xxx.com/video/video_%E8%B6%B3%E7%90%83%E9%AD%94%E6%96%B9_'+str(i)+'.html'

print url

#http://www.xxx.com/video/video_%E8%B6%B3%E7%90%83%E9%AD%94%E6%96%B9_2.html

source=download(url)

data=get_ul(source)

datas=data.split('

')

for each in datas:

ret=re.findall(r"(?<=href=\\").+?(?=\\")|(?<=href=\\').+?(?=\\')" ,each)

for urls in ret:

detial=download(urls)

if detial:

detial_content=GetMiddleStr(detial,'createFlashVideo','m3u8').replace(' ', '')

if detial_content:

end_url_rex=GetMiddleStr(detial_content+".m3u8",'http://','.m3u8')+"m3u8"

#最终的url

#title

sstree = etree.HTML(detial)

ssnodes = sstree.xpath('//*[@id="playVideo"]/div[1]/h2')

for ssn in ssnodes:

name= ssn.text.strip().replace('/h2>', '')

#title=GetMiddleStr(detial,'

').replace(' ', '')

#简介

introduction=GetMiddleStr(detial,'video-info">','').replace(' ', '')

dr = re.compile(r']+>',re.S)

introductions = dr.sub('',introduction)

end_content=introductions.strip().replace('/span>', '')

end_time= time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(time.time()+8*60*60))

#end_times=dt.now().strftime('%Y-%m-%d %H:%i:%S')

saveDB(urls,end_url_rex,name,end_content,str(i),end_time)

def saveDB(current_url,end_url_rex,names,end_content,page,create_time):

#添加select update

sql = 'INSERT INTO test.mytables(current_url,end_url_rex,`names`,end_content,page,create_time)\\

VALUES (%s,%s,%s,%s,%s,%s)'

print sql

cur = conn.cursor()

cur.execute(sql,(current_url,end_url_rex,names,end_content,page,create_time))

cur.close()

conn.commit()

if __name__ == '__main__':

first="http://www.xxx.com/video/video_%E8%B6%B3%E7%90%83%E9%AD%94%E6%96%B9_1.html"

url = urllib2.urlopen(first)

content = url.read()

soup = BeautifulSoup(content)

strs=soup.findAll(attrs={"class":"pagination"})

lists=str(strs[0])

listss=re.findall(r'\\d+',lists)

count=len(listss)

list_string = list(set(listss))

str_num= list_string[-1]

i = 1

while i <= int(str_num):

test_sporttery(i)

i += 1