今天，来对之前自学python做的一个小任务进行复习和总结，首先回顾之前任务的每一个步骤，按照自己个人的思路，一布一步往下做
需求：根据主网站，爬取出大连市各年地区生产总值，观察2010至2015年的趋势
1.获取网页html源码
2.根据html源码解析a标签
3.对a标签进行筛选，返回对应的a标签文本和url字典
4.分别进入各个url网页，解析网页文本内容
5.利用正则提取网页感兴趣的信息
6.将处理后的信息存数据库
第一步：根据url获取主网页源代码
代码如下：
import urllib2
import re
import pymssql
import time
from sgmllib import SGMLParser
#获取页面的html
def getHTML(url):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
html = response.read()
return html html = getHTML("http://www.stats.dl.gov.cn/index.php?m=content&c=index&a=lists&catid=52")
print html
第二部：根据html源码解析a标签
代码如下：
import urllib2
import re
import pymssql
import time
import datetime
from sgmllib import SGMLParser #获取网络页面
def getHTML(url):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
html = response.read()
return html
#获取完整连接内容整个网页包含a标签的内容
def findLinks3(html):
l = []
urls = re.findall(r"<a.*?href=.*?<\/a>",html,re.I|re.S|re.M)
for i in urls:
l.append(i)
return l
html = getHTML("http://www.stats.dl.gov.cn/index.php?m=content&c=index&a=lists&catid=52")
l = findLinks3(html)
for val in l:
print val
第三布：对a标签进行筛选，返回对应的a标签文本和url字典
import urllib2
import re
import pymssql
import time
import datetime
from sgmllib import SGMLParser #获取网络页面
def getHTML(url):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
html = response.read()
return html
#进行模糊筛选（对字符串进行模糊查找，判断是否存在）
def choose(html):
a = -1
if html.find("大连市国民经济和社会发展") == -1:
a=-1
else:
a=1
return a
#获取完整连接内容整个网页包含a标签的内容（有筛选）
def findLinks3(html):
l = []
urls = re.findall(r"<a.*?href=.*?<\/a>",html,re.I|re.S|re.M)
for i in urls:
if choose(i)==1:
l.append(i)
return l
html = getHTML("http://www.stats.dl.gov.cn/index.php?m=content&c=index&a=lists&catid=52")
l = findLinks3(html)
for val in l[1:]:
print val
import urllib2
import re
import pymssql
import time
import datetime
from sgmllib import SGMLParser #获取网络页面
def getHTML(url):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
html = response.read()
return html
#进行模糊筛选（对字符串进行模糊查找，判断是否存在）
def choose(html):
a = -1
if html.find("大连市国民经济和社会发展") == -1:
a=-1
else:
a=1
return a
#获取完整连接内容整个网页包含a标签的内容（有筛选）
def findLinks3(html):
l = []
urls = re.findall(r"<a.*?href=.*?<\/a>",html,re.I|re.S|re.M)
for i in urls:
if choose(i)==1:
l.append(i)
return l
#获取a标签文本内容
def findLinks1(html):
text = []
txts = re.findall(r"<a.*?>(.*?)<\/a>",html,re.I|re.S|re.M)
for i in txts:
if choose(i)==1:
#print i
text.append(i)
return text[0]
#只获取<a>标签链接href中的url<a href="www.www.com"></a>
def findLinks2(html):
url = []
txts = re.findall("(?<=href=\").+?(?=\")|(?<=href=\').+?(?=\')",html,re.I|re.S|re.M)
for i in txts:
#print i
url.append(i)
return url[0]
def getEveryYear(html):
yearUrl ={} #定义空的字典，
l = findLinks3(html) #查找所有超链接
for i in l[1:]:
text = findLinks1(i)
url = findLinks2(i)
yearUrl[text]=url #将超链接文本和url存放在字典中（key-value）
#print text
#print url
return yearUrl html = getHTML("http://www.stats.dl.gov.cn/index.php?m=content&c=index&a=lists&catid=52")
"""
l = findLinks3(html)
for val in l[1:]:
pass
print findLinks1(val)
print findLinks2(val)
"""
d = getEveryYear(html)
for val,key in d.items():
print val
print key
第四 、五：分别进入各个url，提取信息
import urllib2
import re
import pymssql
import time
import datetime
from sgmllib import SGMLParser #获取网络页面
def getHTML(url):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
html = response.read()
return html
#进行模糊筛选（对字符串进行模糊查找，判断是否存在）
def choose(html):
a = -1
if html.find("大连市国民经济和社会发展") == -1:
a=-1
else:
a=1
return a
#获取完整连接内容整个网页包含a标签的内容（有筛选）
def findLinks3(html):
l = []
urls = re.findall(r"<a.*?href=.*?<\/a>",html,re.I|re.S|re.M)
for i in urls:
if choose(i)==1:
l.append(i)
return l
#获取a标签文本内容
def findLinks1(html):
text = []
txts = re.findall(r"<a.*?>(.*?)<\/a>",html,re.I|re.S|re.M)
for i in txts:
if choose(i)==1:
#print i
text.append(i)
return text[0]
#只获取<a>标签链接href中的url<a href="www.www.com"></a>
def findLinks2(html):
url = []
txts = re.findall("(?<=href=\").+?(?=\")|(?<=href=\').+?(?=\')",html,re.I|re.S|re.M)
for i in txts:
#print i
url.append(i)
return url[0]
def getEveryYear(html):
yearUrl ={} #定义空的字典，
l = findLinks3(html) #查找所有超链接
for i in l[1:]:
text = findLinks1(i)
url = findLinks2(i)
yearUrl[text]=url #将超链接文本和url存放在字典中（key-value）
#print text
#print url
return yearUrl
"""
for val in l[1:]:
pass
print findLinks1(val)
print findLinks2(val) d = getEveryYear(html)
for val,key in d.items():
print val
# print key
""" class GetIdList(SGMLParser):
def reset(self):
self.IDlist = []
self.flag = False
self.getdata = False
self.verbatim = 0
SGMLParser.reset(self) def start_div(self, attrs):
if self.flag == True:
self.verbatim +=1 #进入子层div了，层数加1
return
for k,v in attrs: #遍历div的所有属性以及其值
if k == 'class' and v == 'newsBody':#确定进入了<div class='newsBody'>
self.flag = True
return def end_div(self):#遇到</div>
if self.verbatim == 0:
self.flag = False
if self.flag == True:#退出子层div了，层数减1
self.verbatim -=1 def start_p(self, attrs):
if self.flag == False:
return
self.getdata = True def end_p(self):#遇到</p>
if self.getdata:
self.getdata = False def handle_data(self, text):#处理文本
if self.getdata:
self.IDlist.append(text) def printID(self):
for i in self.IDlist:
##print i
pass
return self.IDlist def printtext(url):
html = getHTML(url)
lister = GetIdList()
lister.feed(html)
l = lister.printID()
s=" "
for text in l:
s=s+text
return s[0:500]
def matchRe2(string):
pattern = re.compile(r'([0-9]{1,5}.[0-9])亿元')
#pat = re.compile(r'比上年增长[0-9]{1,5}.[0-9]%')
#pat1 = re.compile(r'第一产业增加值[0-9]{1,5}.[0-9]亿元')
match = pattern.search(string)
if match:
pass
#print "ok"
#print match.group(0)
#print '国民经济生产总值:', pattern.search(string).group()
# print pat1.search(string).group()
#print re.compile(r'现将.*年大连市国民经济和社会发展情况公报如下').search(string).group()
# print re.compile(r'第三产业增加值[0-9]{1,5}.[0-9]亿元').search(string).group()
else:
print 'No match!'
return pattern.search(string).group() def getData(html):
data = {}
d = getEveryYear(html)
for key,value in d.items():
#print key #,value
#download3(value,key)
s=printtext(value)
#print s
#matchRe2(s[20:80])
data[key]= matchRe2(s)
return data
html = getHTML("http://www.stats.dl.gov.cn/index.php?m=content&c=index&a=lists&catid=52")
d = getEveryYear(html) #打印出所有文本内容
"""
for key,val in d.items():
#print val
#print key
s = printtext(val)
print s
""" data = getData(html)
for val,key in data.items():
print val,key
第六步：存数据库
# -*- coding: cp936 -*-
import urllib2
import re
import pymssql
import time
import datetime
from sgmllib import SGMLParser #获取网络页面
def getHTML(url):
request = urllib2.Request(url)
response = urllib2.urlopen(request)
html = response.read()
return html
#进行模糊筛选（对字符串进行模糊查找，判断是否存在）
def choose(html):
a = -1
if html.find("大连市国民经济和社会发展") == -1:
a=-1
else:
a=1
return a
#获取完整连接内容整个网页包含a标签的内容（有筛选）
def findLinks3(html):
l = []
urls = re.findall(r"<a.*?href=.*?<\/a>",html,re.I|re.S|re.M)
for i in urls:
if choose(i)==1:
l.append(i)
return l
#获取a标签文本内容
def findLinks1(html):
text = []
txts = re.findall(r"<a.*?>(.*?)<\/a>",html,re.I|re.S|re.M)
for i in txts:
if choose(i)==1:
#print i
text.append(i)
return text[0]
#只获取<a>标签链接href中的url<a href="www.www.com"></a>
def findLinks2(html):
url = []
txts = re.findall("(?<=href=\").+?(?=\")|(?<=href=\').+?(?=\')",html,re.I|re.S|re.M)
for i in txts:
#print i
url.append(i)
return url[0]
def getEveryYear(html):
yearUrl ={} #定义空的字典，
l = findLinks3(html) #查找所有超链接
for i in l[1:]:
text = findLinks1(i)
url = findLinks2(i)
yearUrl[text]=url #将超链接文本和url存放在字典中（key-value）
#print text
#print url
return yearUrl
"""
for val in l[1:]:
pass
print findLinks1(val)
print findLinks2(val) d = getEveryYear(html)
for val,key in d.items():
print val
# print key
""" class GetIdList(SGMLParser):
def reset(self):
self.IDlist = []
self.flag = False
self.getdata = False
self.verbatim = 0
SGMLParser.reset(self) def start_div(self, attrs):
if self.flag == True:
self.verbatim +=1 #进入子层div了，层数加1
return
for k,v in attrs:#遍历div的所有属性以及其值
if k == 'class' and v == 'newsBody':#确定进入了<div class='entry-content'>
self.flag = True
return def end_div(self):#遇到</div>
if self.verbatim == 0:
self.flag = False
if self.flag == True:#退出子层div了，层数减1
self.verbatim -=1 def start_p(self, attrs):
if self.flag == False:
return
self.getdata = True def end_p(self):#遇到</p>
if self.getdata:
self.getdata = False def handle_data(self, text):#处理文本
if self.getdata:
self.IDlist.append(text) def printID(self):
for i in self.IDlist:
##print i
pass
return self.IDlist def printtext(url):
html = getHTML(url)
lister = GetIdList()
lister.feed(html)
l = lister.printID()
s=" "
for text in l:
s=s+text
return s[0:500]
def matchRe2(string):
pattern = re.compile(r'([0-9]{1,5}.[0-9])亿元')
#pat = re.compile(r'比上年增长[0-9]{1,5}.[0-9]%')
#pat1 = re.compile(r'第一产业增加值[0-9]{1,5}.[0-9]亿元')
match = pattern.search(string)
if match:
pass
#print "ok"
#print match.group(0)
#print '国民经济生产总值:', pattern.search(string).group()
# print pat1.search(string).group()
#print re.compile(r'现将.*年大连市国民经济和社会发展情况公报如下').search(string).group()
# print re.compile(r'第三产业增加值[0-9]{1,5}.[0-9]亿元').search(string).group()
else:
print 'No match!'
return pattern.search(string).group() def getData(html):
data = {}
d = getEveryYear(html)
for key,value in d.items():
#print key #,value
#download3(value,key)
s=printtext(value)
#print s
#matchRe2(s[20:80])
data[key]= matchRe2(s)
return data class MSSQL:
def __init__(self,host,user,pwd,db):
self.host = host
self.user = user
self.pwd = pwd
self.db = db def __GetConnect(self):
if not self.db:
raise(NameError,"没有设置数据库信息")
self.conn = pymssql.connect(host=self.host,user=self.user,password=self.pwd,database=self.db,charset="utf8")
cur = self.conn.cursor()
if not cur:
raise(NameError,"连接数据库失败")
else:
return cur def ExecQuery(self,sql):
cur = self.__GetConnect()
cur.execute(sql)
resList = cur.fetchall() #查询完毕后必须关闭连接
self.conn.close()
return resList def ExecNonQuery(self,sql):
cur = self.__GetConnect()
cur.execute(sql)
self.conn.commit()
self.conn.close() def OnlyCharNum(s,oth=''):
s2 = s.lower();
fomart = '.0123456789'
for c in s2:
if not c in fomart:
s = s.replace(c,'');
return s;
#写sql
def makesql(year,money,time):
sql = "insert into Innocellence_TimeSheet_GDPRecord values("+year+","+money+","+time+")"
return sql #创建数据库实例
ms = MSSQL(host="localhost",user="sa",pwd="",db="testdb")
#先删除旧数据 #查询数据
"""reslist = ms.ExecQuery("select year,round(amount,1) from Innocellence_TimeSheet_GDPRecord order by year")
for i in reslist:
print i"""
#先清空数据
ms.ExecNonQuery("delete from Innocellence_TimeSheet_GDPRecord ")
html = getHTML("http://www.stats.dl.gov.cn/index.php?m=content&c=index&a=lists&catid=52")
d = getEveryYear(html)
data = getData(html)
for key,val in data.items():
print key,val
sql = makesql(key[:4],OnlyCharNum(val),"'"+time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(time.time()))+"'")
print sql
ms.ExecNonQuery(sql)