贡献个EPG获取的爬虫，开源

3m***

从tianmaotv获取，代码开源。各位自由发挥
首次使用python
设置了代码回复可见，只为统计下载量
论坛的hide代码有问题的，代码框140强行加入了【hide】。各位自行删除【hide】吧。
修改成下图的样子

代码如下

1. import sys
   
2. import requests
   
3. import re
   
4. import time
   
5. import codecs
   
6. import json
   
7. import xml.etree.ElementTree as ET
   
8. from datetime import datetime, date, time, timedelta
   
9. from bs4 import BeautifulSoup
   
10. from xml.dom import minidom
    
11. from xpinyin import Pinyin
    
12. 
    
13. 
    
14. if sys.version_info[0] == 2:
    
15.     from urllib2 import urlopen  # Python 2
    
16. else:
    
17.     from urllib.request import urlopen  # Python3
    
18. 
    
19. def get_week_backup():
    
20.     now=datetime.now()
    
21.     week=now.strftime('%w')
    
22.     if int(week) == 7:
    
23.         w=[week,str(1)]
    
24.     else:
    
25.         w=[week,str(int(week)+1)]
    
26.     return w
    
27. 
    
28. def get_week():
    
29.     now=datetime.now()
    
30.     week=now.strftime('%w')
    
31.     wd=int(week)
    
32.     w=[]
    
33.     for i in range(wd,8):
    
34.         w.append(str(i))
    
35.     return w
    
36. 
    
37. def saveXML(root, filename, indent="\t", newl="\n", encoding="utf-8"):
    
38.     rawText = ET.tostring(root)
    
39.     dom = minidom.parseString(rawText)
    
40.     with codecs.open(filename, 'w', 'utf-8') as f:
    
41.         #writer = codecs.lookup('utf-8')[3](f)
    
42.         dom.writexml(f, "", indent, newl, encoding)
    
43. 
    
44. def ch_dict():
    
45.     headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0',
    
46.                    'Connection': 'keep-alive', 'Cache-Control': 'no-cache'}
    
47.     url="https://www.tianmaotv.cn/tv/"
    
48.     ch_list=["type_101","type_102","tv_453","tv_526"]
    
49.     dict_url={}
    
50.     dict_name={}
    
51.     p=Pinyin()
    
52.     tmp_dic={}
    
53. 
    
54.     for ch in ch_list:
    
55.         r = requests.get(url+ch, headers=headers)               
    
56.         r.encoding=r.apparent_encoding
    
57.         soup = BeautifulSoup(r.text, 'lxml')
    
58.         
    
59.         list_program_div = soup.find(
    
60.                 name='dl', attrs={"class": "tv-station-list"}).find_all('a')
    
61.         
    
62.         for tagprogram in list_program_div:
    
63.             r=re.compile(r"\/jmb")
    
64.             if r.match(tagprogram["href"]):
    
65.                 dict_url[tagprogram.string]=tagprogram["href"]
    
66.                 tmp=p.get_initials(tagprogram.string, u'')
    
67.                 #flages=tmp is tmp_dic
    
68.                 if tmp in tmp_dic:
    
69.                     tmp_dic[tmp+"1"]=tagprogram.string   
    
70.                 else:
    
71.                     tmp_dic[tmp]=tagprogram.string               
    
72.                 '''
    
73.                 name_list_temp=list(dict_name.values())
    
74.                 flags=tagprogram.string in dict_name
    
75.                 if not flags:
    
76.                     dict_name[tagprogram.string]=p.get_initials(tagprogram.string, u'')
    
77.                 for ss in name_list_temp:
    
78.                     if tmp == ss:
    
79.                         print(tmp,tmp+"1",tagprogram.string)
    
80.                         dict_name[tagprogram.string]=p.get_initials(tagprogram.string, u'')+"1"
    
81.                         #print(dict_name)'''
    
82.     dict_name={v:k for k, v in tmp_dic.items()}
    
83.     return dict_url,dict_name
    
84. 
    
85. def get_channel_programme(url_name_py,real_rul):
    
86.     headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0',
    
87.                'Connection': 'keep-alive', 'Cache-Control': 'no-cache'}
    
88.    
    
89.     r = requests.get("https://www.tianmaotv.cn"+real_rul, headers=headers)
    
90.     r.encoding=r.apparent_encoding
    
91.     soup = BeautifulSoup(r.text, 'lxml')
    
92.     #print(soup)
    
93. 
    
94.     timestart={}
    
95.     timestop={}
    
96.     channel_title={}
    
97. 
    
98.     list_program_div = soup.find(name='dl', attrs={"class": "program-list"}).find_all('dd')
    
99.     #print(list_program_div)
    
100.     for i in list_program_div:
     
101.         times=i.time.string.strip()
     
102.         times=datetime.strptime("2019-"+times,'%Y-%m-%d %H:%M')
     
103.         timestart[times.strftime("%Y%m%d%H%M%S")]=i.contents[2].strip()
     
104.     return timestart
     
105. 
     
106. 
     
107. aa=ch_dict()
     
108. channel_url=aa[0]
     
109. channel_py=aa[1]
     
110. '''
     
111. with open('e:\\python\\tianmaotv\\data.json', 'w',encoding='utf-8') as f:
     
112.     json.dump(aa, f,sort_keys=False, indent=4,  separators=(',',':'),ensure_ascii=False)
     
113. 
     
114. print(channel_py.items)
     
115. print(channel_url.items)
     
116. '''
     
117. new_root = ET.Element('tv')
     
118. new_root.set("generator-info-name", "3mile")
     
119. new_root.set("generator-info-url", "https://3mile.top")
     
120. new_root.tail="\n"
     
121. for k,v in channel_py.items():
     
122.     child = ET.SubElement(new_root,"channel")
     
123.     #child.tail="\n"
     
124.     child.set("id",v)
     
125.     child_name=ET.SubElement(child,"display-name")
     
126.     #child.tail="\n"
     
127.     child_name.set("lang","zh")
     
128.     child_name.text=k
     
129.     child_url=ET.SubElement(child,'url')
     
130.     #child_url.tail='\n'
     
131.     child_url.text="https://tianmao.tv"+channel_url[k]
     
132. 
     
133. #ET.dump(new_root)
     
134. wday=get_week()
     
135. for k,v in channel_url.items():
     
136.     programme={}
     
137.     print("正在获取 "+k+" EPG信息")
     
138.     for i in wday:
     
139.         url=re.sub(r'\/, "", v)+"_w"+i+"/"
     
140.         progr=get_channel_programme(channel_py[k],url)
     
141.         programme.update(progr)
     
142.    
     
143.     tmp=list(programme.items())
     
144.     list_time=list(programme.keys())
     
145.     list_title=list(programme.values())
     
146. 
     
147.     for t in range(len(list_time)):
     
148.         tit=list_title[t]
     
149.         begin=list_time[t]
     
150.         if t+1<len(list_time):
     
151.             end=list_time[t+1]
     
152.         else:
     
153.             ta1=datetime.strptime(list_time[t],'%Y%m%d%H%M%S')
     
154.             ta1=ta1+timedelta(hours=1)
     
155.             end=ta1.strftime('%Y%m%d%H%M%S')
     
156. 
     
157.         programme_sub=ET.SubElement(new_root,"programme")
     
158.         #programme_sub.tail='\n'
     
159.         programme_sub.set("start",begin+" +0800")
     
160.         programme_sub.set("stop",end+" +0800")
     
161.         programme_sub.set("channel",channel_py[k])
     
162.         
     
163.         programme_title=ET.SubElement(programme_sub,"title")
     
164.         programme_title.set("lang","zh")
     
165.         programme_title.text=tit
     
166.     print("已经获取 "+k+"EPG内容")
     
167. 
     
168. saveXML(new_root,"e.xml")
     

复制代码

mya***

可以像原来超级直播自定义那样方便使用吗？

ai2***

多少个多少如果洞若观火突然很坦然发货

ken***

可以像原来超级直播自定义那样方便使用吗？

wuyanz***

贡献个EPG获取的爬虫，开源

ly***

思考思考了

Amb***

贡献个EPG获取的爬

pq2***

谢谢分享，这个不错的样子

yns***

分享万岁！谢谢啊！

jack***

谢谢分享。。。。

xlht***

谢谢楼主分享

zy76***

谢谢楼主分享

plh***

谢谢楼主分享EPG获取的爬虫

AK***

谢谢大佬分享

iptv***

太好了！实在好！