第一篇博客（python爬取小故事网并写入mysql）

 1 import requests as rq
 2 import re
 3 import codecs
 4 import queue
 5 import pymysql
 6 from urllib.request import urlopen
 7 from bs4 import BeautifulSoup
 8 
 9 tasks = queue.Queue()  # 链接队列
10 tasks_pass = set()  # 已队列过的链接
11 results = {}  # 结果变量
12 count = 0  # 爬取页面总数
13 tasks.put(‘/index.html‘)  # 把主页加入到链接队列
14 tasks_pass.add(‘/index.html‘)  # 把主页加入到已队列链接
15 db = pymysql.connect("localhost","testuser","test123","TESTDB",charset=‘gbk‘)
16 dbc = db.cursor()
17 
18 while count<=100:
19     url = tasks.get() #取出一个链接
20     url = ‘http://wap.xigushi.com‘+url
21     web = rq.get(url).content.decode(‘gbk‘) #这里的编码要看实际情形而定
22     urls = re.findall(‘href="(/.*?)"‘, web) #查找所有站内链接
23     for u in urls:
24         if u not in tasks_pass: #把还没有队列过的链接加入队列
25             tasks.put(u)
26             tasks_pass.add(u)
27     html=urlopen(url)
28     bsObj=BeautifulSoup(html.read(),"lxml")
29     if not (re.search(‘images‘,url)):
30         # print(re.search(‘images‘, url))
31         text=bsObj.title.get_text()
32         print(url + ‘   ‘ + text)
33         sql = "insert into data1(url,title) values(%s,%s);"
34         data=(url,text)
35         dbc.execute(sql,data)
36         db.commit()
37     else:
38         if (re.search(‘images‘,url).span()):
39             print(‘---------------------------skipping--------------------------------------------‘)
40     count += 1
41 db.close()
42 
43 with codecs.open(‘results.txt‘, ‘w‘, encoding=‘utf-8‘) as f:
44         f.write(‘\n‘.join(results.items()))