爬取小說網站的小說，並保存到數據庫
第一步：先獲取小說內容
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import urllib2,re
domain = 'http://www.quanshu.net'
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"
}
def getTypeList(pn=1): #獲取分類列表的函數
req = urllib2.Request('http://www.quanshu.net/map/%s.html' % pn) #實例將要請求的對象
req.headers = headers #替換所有頭信息
#req.add_header() #添加單個頭信息
res = urllib2.urlopen(req) #開始請求
html = res.read().decode('gbk') #decode解碼，解碼成Unicode
reg = r'<a href="(/book/.*?)" target="_blank">(.*?)</a>'
reg = re.compile(reg) #增加匹配效率 正則匹配返回的類型爲List
return re.findall(reg,html)
def getNovelList(url): #獲取章節列表函數
req = urllib2.Request(domain + url)
req.headers = headers
res = urllib2.urlopen(req)
html = res.read().decode('gbk')
reg = r'<li><a href="(.*?)" title=".*?">(.*?)</a></li>'
reg = re.compile(reg)
return re.findall(reg,html)
def getNovelContent(url): #獲取章節內容
req = urllib2.Request(domain + url)
req.headers = headers
res = urllib2.urlopen(req)
html = res.read().decode('gbk')
reg = r'style5\(\);</script>(.*?)<script type="text/javascript">style6\(\)'
return re.findall(reg,html)[0]
if __name__ == '__main__':
for type in range(1,10):
for url,title in getTypeList(type):
for zurl,ztitle in getNovelList(url):
print u'正則爬取----%s' %ztitle
content = getNovelContent(url.replace('index.html',zurl))
print content
break
break執行後結果如下：
第二步：存儲到數據庫
1、設計數據庫
1.1 新建庫：novel
1.2 設計表：novel
1.3 設計表：chapter
並設置外鍵
2、編寫腳本
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import urllib2,re
import MySQLdb
class Sql(object):
conn = MySQLdb.connect(host='192.168.19.213',port=3306,user='root',passwd='Admin123',db='novel',charset='utf8')
def addnovels(self,sort,novelname):
cur = self.conn.cursor()
cur.execute("insert into novel(sort,novelname) values(%s , '%s')" %(sort,novelname))
lastrowid = cur.lastrowid
cur.close()
self.conn.commit()
return lastrowid
def addchapters(self,novelid,chaptername,content):
cur = self.conn.cursor()
cur.execute("insert into chapter(novelid,chaptername,content) values(%s , '%s' ,'%s')" %(novelid,chaptername,content))
cur.close()
self.conn.commit()
domain = 'http://www.quanshu.net'
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"
}
def getTypeList(pn=1): #獲取分類列表的函數
req = urllib2.Request('http://www.quanshu.net/map/%s.html' % pn) #實例將要請求的對象
req.headers = headers #替換所有頭信息
#req.add_header() #添加單個頭信息
res = urllib2.urlopen(req) #開始請求
html = res.read().decode('gbk') #decode解碼，解碼成Unicode
reg = r'<a href="(/book/.*?)" target="_blank">(.*?)</a>'
reg = re.compile(reg) #增加匹配效率 正則匹配返回的類型爲List
return re.findall(reg,html)
def getNovelList(url): #獲取章節列表函數
req = urllib2.Request(domain + url)
req.headers = headers
res = urllib2.urlopen(req)
html = res.read().decode('gbk')
reg = r'<li><a href="(.*?)" title=".*?">(.*?)</a></li>'
reg = re.compile(reg)
return re.findall(reg,html)
def getNovelContent(url): #獲取章節內容
req = urllib2.Request(domain + url)
req.headers = headers
res = urllib2.urlopen(req)
html = res.read().decode('gbk')
reg = r'style5\(\);</script>(.*?)<script type="text/javascript">style6\(\)'
return re.findall(reg,html)[0]
mysql = Sql()
if __name__ == '__main__':
for sort in range(1,10):
for url,title in getTypeList(sort):
lastrowid = mysql.addnovels(sort, title)
for zurl,ztitle in getNovelList(url):
print u'正則爬取----%s' %ztitle
content = getNovelContent(url.replace('index.html',zurl))
print u'正在存儲----%s' %ztitle
mysql.addchapters(lastrowid,ztitle,content)3、執行腳本
4、查看數據庫
可以看到已經存儲成功了。
報錯：
_mysql_exceptions.OperationalError: (1364, "Field 'novelid' doesn't have a default value")
解決：執行sql語句
SELECT @@GLOBAL.sql_mode;
SET @@GLOBAL.sql_mode="NO_ENGINE_SUBSTITUTION";
報錯參考：http://blog.sina.com.cn/s/blog_6d2b3e4901011j9w.html