Python简单爬虫记录

 1 link = ‘http://news.sina.com.cn/‘
 2 res = requests.get(link)
 3 res.encoding = ‘utf-8‘ #设置文本的编码格式是utf-8的文件格式
 4 soup = BeautifulSoup(res.text, ‘html.parser‘) #通过res中的成员变量.text来得到HTML的文本res.text
 5 alink = soup.select(‘a‘) #选择class模块中的a来作为提取的目标的判定条件：<a href="http://mil.news.sina.com.cn/"><span class="titName ptn_05">军事</span></a>
 6 DATA = set() #创建一个set集合
 7 Cookies = [‘军事‘, ‘教育‘, ‘科技‘, ‘文化‘] #创建一个目标提取项目
 8 for link in alink:
 9     if link.text in Cookies: #alink中包含了所有的以a开头的class文本，link.text提取了其中一个link的文本内容
10         Temp = ‘The title of link ‘+link.text+‘ is :‘+link[‘href‘] #使用link[‘herf‘]来取herf对应的字典字符串，也就是对应的链接
11         DATA.add(Temp) #在DATA数据中加入满足正则要求的文本文件
12 for Info in DATA:
13     print(Info)
14 Check = input(‘Please input the content you want to see:‘)
15 Str = ‘‘
16 for W in list(DATA):
17     if W.find(Check) != -1:
18         Str = Str + W + ‘\n‘
19 File = open(‘C:\\Users\\Administrator\Desktop\Python爬虫准备\demo\Info1.txt‘, ‘w‘) #将取得的文件写入到文件夹当中
20 File.writelines(Str)
21 File.close()
22 
23 HTML = ‘http://book.weibo.com/newcms/tp_p4c51t160.html‘
24 res = requests.get(HTML)
25 res.encoding = ‘utf-8‘
26 soup = BeautifulSoup(res.text, ‘html.parser‘)
27 title = soup.select(‘.S_title‘)
28 print(title[0].text)
29 content = soup.select(‘.S_explain‘)
30 print(content[0].text)
31 Count = soup.select(‘.book_vote‘)
32 Bname = soup.select(‘.book_name‘)
33 Aname = soup.select(‘.book_author‘)
34 Blink = soup.select(‘a‘)
35 Info = ‘‘
36 for i in range(len(Bname)):
37     Info = Info + Bname[i].text + ‘-->‘ + Aname[i].text + ‘(‘ +38            Count[i].text.replace(‘ ‘, ‘‘) + ‘)‘ + ‘--link:‘ +39            Blink[i*4][‘href‘]+‘\n\n‘
40 print(Info)
41 Data = title[0].text + ‘\n‘ + content[0].text + ‘\n‘ + Info
42 F = open(‘C:\\Users\\Administrator\Desktop\Python爬虫准备\demo\Info2.txt‘, ‘w‘)
43 F.writelines(Data)
44 F.close()
45 
46 Init_link = ‘https://www.douyu.com/directory/all‘
47 Data = requests.get(Init_link)
48 Data.encoding = ‘utf-8‘
49 soup = BeautifulSoup(Data.text, ‘html.parser‘)
50 Res = soup.select(‘.mes‘)
51 Count = soup.select(‘p‘)
52 for i in Res:
53     if i.text.find(‘英雄联盟‘) != -1:
54         Str = i.text.replace(‘ ‘, ‘‘).replace(‘\n‘, ‘‘)
55         print(Str)
56         print(Str[len(Str)-3:len(Str)])
57 print(len(Res))