1 #coding: UTF-8

2 importos3 importsys4 importrequests5 importurllib.request,io6 from html.parser importHTMLParser7

8 #全局变量

9

10 id_list = set() #保存视频ID的列表

11 id_dict = {} #保存id和对应子视频数目

12 cookies = {} #保存cookies

13

14 #HTML解析类

15 classMyHTMLParser(HTMLParser):16 def __init__(self, key, attr):17 HTMLParser.__init__(self)18 self.links =[]19 self.keys =key20 self.attr =attr21 defhandle_starttag(self, tag, attrs):22 #print "Encountered the beginning of a %s tag" % tag

23 #if tag == "source":

24 if tag ==self.keys:25 if len(attrs) ==0:26 pass

27 else:28 for (variable, value) inattrs:29 #if variable == "src":

30 if variable ==self.attr:31 self.links.append(value)32

33

34 #解析cookies字典

35 defgetCookies(cookies_str):36 globalcookies37 for line in cookiesStr.split(';'):38 #其设置为1就会把字符串拆分成2份

39 name, value = line.strip().split('=', 1)40 cookies[name] =value41

42 defgetHtml(url, key, value):43 globalcookies44 r = requests.get(url, cookies=cookies)45 content = r.content.decode('UTF-8')46 hp = MyHTMLParser("source", "src")47 hp.feed(content)48 hp.close()49 print(hp.links)50 for link inhp.links:51 link_str =str(link)52 if link_str.find(".mp4") >=0:53 downloadFile(link, key, value)54 else:55 print("没有找到对应视频")56

57

58 #获取课程数目

59 defgetCourseNum(url):60 globalcookies61 url_list =set()62 r = requests.get(url, cookies=cookies)63 content = r.content.decode('UTF-8')64 hp = MyHTMLParser("a", "href")65 hp.feed(content)66 hp.close()67 for link inhp.links:68 link_str =str(link)69 if link_str.find("http://www.jikexueyuan.com/course/") >= 0 and link_str.find(".html?ss=1") >=0:70 url_list.add(link_str)71 return url_list.__len__()72

73 #获取所有视频ID，根据目录网页

74 defgetIdList(root):75 globalcookies76 r = requests.get(root, cookies=cookies)77 content = r.content.decode('UTF-8')78 hp = MyHTMLParser("a", "href")79 hp.feed(content)80 hp.close()81 #print(hp.links)

82 #声明引用全局id_list,在最上面定义

83 globalid_list84 globalid_dict85

86 for link inhp.links:87 link_str =str(link)88 if link_str.find("http://www.jikexueyuan.com/course/") >= 0 and link_str.find(".html")>=0:89 #print(link)

90 c_id = link_str.lstrip("http://www.jikexueyuan.com/course/").rstrip(".html")91 if c_id not inid_list:92 id_dict[c_id] =getCourseNum(link_str)93 print(c_id, id_dict[c_id])94 id_list.add(c_id)95 print(id_dict)96

97 defdownloadFile(url, key, value):98 #url = 'http://cv4.jikexueyuan.com/10de45bbf83e450ff5e11ff4599d7166/201603202253/cocos2d-x/course_712/01/video/c712b_01_h264_sd_960_540.mp4'

99 r =requests.get(url)100 file_name = str(key)+"_"+str(value)+".mp4"

101 with open(file_name, "wb") as code:102 code.write(r.content)103

104 if __name__=="__main__":105 count =0106 #解析cookies 利用免费时间下载需要视频，需要账号的cookies

107 cookiesStr = "通过谷歌浏览器可以获取"

108 getCookies(cookiesStr)109

110

111 root = "http://ke.jikexueyuan.com/xilie/331?huodong=shequn_0307"

112 getIdList(root)113

114 head = "http://www.jikexueyuan.com/course/"

115

116 for key inid_dict:117 if id_dict[key] <=0:118 print(id_dict[key],"没有数据")119 break

120 for i in range(1, id_dict[key]+1):121 url = head+key+"_"+str(i)+".html?ss=1"

122 print("下载:")123 print(url)124 count += 1

125 getHtml(url, key, i)126 print("视频总数：")127 print(count)