B站标题/子标题/url爬取示例(requests+re)

 #coding:utf-8
 2 __author__ = "zhoumi"
 3
 
 4 import requests
 5 import re
 6 import urllib
 7 ‘‘‘
 8 本文档目的在于获得：
 9 1、一级目录与其对应链接的字典,如下形式
10     dictinfo = {一级目录:链接}
11 2、二级目录与其对应链接的字典,如下形式
12     dict2info = {二级目录:链接}
13 3、一级目录与二级目录对应的字典，如下形式
14     dict3info = {一级目录:[二级目录]}
15 ‘‘‘
16 
17 #获得待解析的页面
18 #首先用raise_for_status处理异常：若请求不成功，抛出异常
19 def getText(url):
20         source = requests.get(url)
21         source.raise_for_status()
22         source.encoding = source.apparent_encoding
23         return(source.text)
24 
25 #返回分类名(keys)及对应链接(value)的字典
26 #dictinfo = {name1list:html1list}
27 #例如：动画:www.bilibili.donghua.com,........
28 def getfirsttitle(source):
29     text = re.findall(r‘a class.*?div class‘,source)
30     namelist = []
31     htmllist = []
32     dictinfo = {}
33     for i in text:
34         namelist.append(i.split("><em>")[1].split("</em>")[0])
35         htmllist.append(i.split(‘href="//‘)[1].split(‘"><em>‘)[0])
36     for i in range(len(namelist) - 1):
37         dictinfo[namelist[i]] = htmllist[i]
38     return dictinfo
39 
40 #返回二级分类的keys(分类名)和values(对应链接)的字典
41 #dict2info = {name2list:html2list}
42 def getsecondtitle(source):
43     text2 = re.findall(r‘a href.*?<em></em></b></a></li>‘,source)
44     name2list = []
45     html2list = []
46     dict2info = {}
47     for i in text2:
48         name2list.append(i.split(‘><b>‘)[1].split(‘<em>‘)[0])
49         html2list.append(i.split(‘a href="//‘)[1].split(‘"><b>‘)[0])
50     for i in range(len(name2list) - 1):
51         dict2info[name2list[i]] = html2list[i]
52     return dict2info
53 
54 #获得一级分类和二级分类的分类名的字典
55 #dict3info = {name1list:[name2list]}
56 def getfirst2second(source):
57     text3 = re.findall(r‘"m-i".*?</ul‘,source,re.S)
58     dict3info = {}
59     middletitle = []
60     for i in text3:
61         #获得出各个一级标题
62         title = i.split(‘><b>‘)[0].split(‘</em>‘)[0].split(‘<em>‘)[1]
63         #获得各一级标题的子标题
64         childtitle = i.split(‘><b>‘)
65         dict3info[title] = childtitle
66         for j in range(len(childtitle) - 1):
67             childtitle[j] = childtitle[j + 1]
68         #处理冗余
69         childtitle.pop()
70         for k in childtitle:
71             middletitle.append(k.split(‘<em>‘)[0])
72         #每处理完一个title的childtitle，就执行存储语句
73         dict3info[title] = middletitle
74         #初始化传递列表
75         middletitle = []
76     return dict3info
77 
78 
79 #——————————————————————————————————————————————

80 ##导入字典{二级分类名：urls2}计划使用urllib库
81 ‘‘‘
82 url为dict_2_url2字典里面的url2
83 本文本块目的在于获取二级分类页面的源视频链接和视频名称
84 并生成最终可调用字典{source_name:source_url}
85 
86 url = dict_2_urls.values()
87 ‘‘‘
88 
89 def gettext(url):
90     source = requests.get(url)
91     source.raise_for_status()
92     source.encoding = source.apparent_encoding
93     return source.text
94 
95 def download(source):
96     text = re.findall(r‘<video> src="blob:.*?"></video>‘,source)
97     html = text.split(‘<video> src="‘)[1].split(‘"></video>‘)[0]
98     pass

1 import urllib.request
2 import urllib.parse
3 
4 def gettext(url):
5     source = urllib.request.urlopen(url,timeout=30)
6     return source.read()
7 url = ‘https://www.bilibili.com/video/av11138658/‘
8 text = gettext(url)
9 print(text)