python 论坛回复可见,贡献个EPG获取的爬虫，开源 - iptv信源、网络视频直播ip资源、直播代码 - 恩山无线论坛 - Powered by Discuz!...

import sys

import requests

import re

import time

import codecs

import json

import xml.etree.ElementTree as ET

from datetime import datetime, date, time, timedelta

from bs4 import BeautifulSoup

from xml.dom import minidom

from xpinyin import Pinyin

if sys.version_info[0] == 2:

from urllib2 import urlopen  # Python 2

else:

from urllib.request import urlopen  # Python3

def get_week_backup():

now=datetime.now()

week=now.strftime('%w')

if int(week) == 7:

w=[week,str(1)]

else:

w=[week,str(int(week)+1)]

return w

def get_week():

now=datetime.now()

week=now.strftime('%w')

wd=int(week)

w=[]

for i in range(wd,8):

w.append(str(i))

return w

def saveXML(root, filename, indent="\t", newl="\n", encoding="utf-8"):

rawText = ET.tostring(root)

dom = minidom.parseString(rawText)

with codecs.open(filename, 'w', 'utf-8') as f:

#writer = codecs.lookup('utf-8')[3](f)

dom.writexml(f, "", indent, newl, encoding)

def ch_dict():

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0',

'Connection': 'keep-alive', 'Cache-Control': 'no-cache'}

url="https://www.tianmaotv.cn/tv/"

ch_list=["type_101","type_102","tv_453","tv_526"]

dict_url={}

dict_name={}

p=Pinyin()

tmp_dic={}

for ch in ch_list:

r = requests.get(url+ch, headers=headers)

r.encoding=r.apparent_encoding

soup = BeautifulSoup(r.text, 'lxml')

list_program_div = soup.find(

name='dl', attrs={"class": "tv-station-list"}).find_all('a')

for tagprogram in list_program_div:

r=re.compile(r"\/jmb")

if r.match(tagprogram["href"]):

dict_url[tagprogram.string]=tagprogram["href"]

tmp=p.get_initials(tagprogram.string, u'')

#flages=tmp is tmp_dic

if tmp in tmp_dic:

tmp_dic[tmp+"1"]=tagprogram.string

else:

tmp_dic[tmp]=tagprogram.string

'''

name_list_temp=list(dict_name.values())

flags=tagprogram.string in dict_name

if not flags:

dict_name[tagprogram.string]=p.get_initials(tagprogram.string, u'')

for ss in name_list_temp:

if tmp == ss:

print(tmp,tmp+"1",tagprogram.string)

dict_name[tagprogram.string]=p.get_initials(tagprogram.string, u'')+"1"

#print(dict_name)'''

dict_name={v:k for k, v in tmp_dic.items()}

return dict_url,dict_name

def get_channel_programme(url_name_py,real_rul):

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0',

'Connection': 'keep-alive', 'Cache-Control': 'no-cache'}

r = requests.get("https://www.tianmaotv.cn"+real_rul, headers=headers)

r.encoding=r.apparent_encoding

soup = BeautifulSoup(r.text, 'lxml')

#print(soup)

timestart={}

timestop={}

channel_title={}

list_program_div = soup.find(name='dl', attrs={"class": "program-list"}).find_all('dd')

#print(list_program_div)

for i in list_program_div:

times=i.time.string.strip()

times=datetime.strptime("2019-"+times,'%Y-%m-%d %H:%M')

timestart[times.strftime("%Y%m%d%H%M%S")]=i.contents[2].strip()

return timestart

aa=ch_dict()

channel_url=aa[0]

channel_py=aa[1]

'''

with open('e:\\python\\tianmaotv\\data.json', 'w',encoding='utf-8') as f:

json.dump(aa, f,sort_keys=False, indent=4,  separators=(',',':'),ensure_ascii=False)

print(channel_py.items)

print(channel_url.items)

'''

new_root = ET.Element('tv')

new_root.set("generator-info-name", "3mile")

new_root.set("generator-info-url", "https://3mile.top")

new_root.tail="\n"

for k,v in channel_py.items():

child = ET.SubElement(new_root,"channel")

#child.tail="\n"

child.set("id",v)

child_name=ET.SubElement(child,"display-name")

#child.tail="\n"

child_name.set("lang","zh")

child_name.text=k

child_url=ET.SubElement(child,'url')

#child_url.tail='\n'

child_url.text="https://tianmao.tv"+channel_url[k]

#ET.dump(new_root)

wday=get_week()

for k,v in channel_url.items():

programme={}

print("正在获取 "+k+" EPG信息")

for i in wday:

url=re.sub(r'\/, "", v)+"_w"+i+"/"

progr=get_channel_programme(channel_py[k],url)

programme.update(progr)

tmp=list(programme.items())

list_time=list(programme.keys())

list_title=list(programme.values())

for t in range(len(list_time)):

tit=list_title[t]

begin=list_time[t]

if t+1

end=list_time[t+1]

else:

ta1=datetime.strptime(list_time[t],'%Y%m%d%H%M%S')

ta1=ta1+timedelta(hours=1)

end=ta1.strftime('%Y%m%d%H%M%S')

programme_sub=ET.SubElement(new_root,"programme")

#programme_sub.tail='\n'

programme_sub.set("start",begin+" +0800")

programme_sub.set("stop",end+" +0800")

programme_sub.set("channel",channel_py[k])

programme_title=ET.SubElement(programme_sub,"title")

programme_title.set("lang","zh")

programme_title.text=tit

print("已经获取 "+k+"EPG内容")

saveXML(new_root,"e.xml")