Internet radio browser GUI for music/video streams from various directory services.

⌈⌋ ⎇ branch:  streamtuner2


Check-in [466f591a1a]

Overview
Comment:radionet updated to extract from horrendous new html pages. Perhaps switching to extracting just the JSON blob later on. urn: resolution remains unchanged.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 466f591a1a46c8c897f7621b41277885f526434b
User & Date: mario on 2020-05-12 15:57:26
Other Links: manifest | tags
Context
2020-05-12
16:17
temporary fix for MyOggRadio being offline. check-in: 7efd6c6ea2 user: mario tags: trunk
15:57
radionet updated to extract from horrendous new html pages. Perhaps switching to extracting just the JSON blob later on. urn: resolution remains unchanged. check-in: 466f591a1a user: mario tags: trunk
15:56
Update radiolist plugin for new wordpress site; now uses genre categories instead of countries. check-in: c952ce442c user: mario tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Modified contrib/radionet.py from [06bc97f343] to [6f48b334fd]. 

1
2
3
4
5
6
7
8
9
10
11
12
13

# encoding: UTF-8
# api: streamtuner2
# title: radio.net
# description: Europe's biggest radio platform
# url: http://radio.net/
# version: 0.9
# type: channel
# category: radio
# png:
#   iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAt0lEQVR42mNgYGD4r+Ar/F/BDwkD+SBxojBMs1mLPBArgGlFqEEENYMNQNLsukIDYkirAvGu
#   ABsA1OC6XOP/5f8nwIaYAg0k2gBFsAsgTgcZkvnfDugFEeK9AFKsCPMG0CU6eZJgQ4R1eP8H7LLEivWyFJANQcQCLPBAmkGG4MJohmA6C6QA5gI5OxEUDNII
#   MwSvASBFIA3ociCxkWQAKMDICkSQIpgh2LDnSmP80YhsCFEJiRIMADpmeUOpqgjRAAAAAElFTkSuQmCC
# priority: optional






|








1
2
3
4
5
6
7
8
9
10
11
12
13

# encoding: UTF-8
# api: streamtuner2
# title: radio.net
# description: Europe's biggest radio platform
# url: http://radio.net/
# version: 1.0
# type: channel
# category: radio
# png:
#   iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAt0lEQVR42mNgYGD4r+Ar/F/BDwkD+SBxojBMs1mLPBArgGlFqEEENYMNQNLsukIDYkirAvGu
#   ABsA1OC6XOP/5f8nwIaYAg0k2gBFsAsgTgcZkvnfDugFEeK9AFKsCPMG0CU6eZJgQ4R1eP8H7LLEivWyFJANQcQCLPBAmkGG4MJohmA6C6QA5gI5OxEUDNII
#   MwSvASBFIA3ociCxkWQAKMDICkSQIpgh2LDnSmP80YhsCFEJiRIMADpmeUOpqgjRAAAAAElFTkSuQmCC
# priority: optional
︙︙
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48

49



50
51
52
53
54
55
56
57
58
59



60
61
62
63
64
65
66

67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85

86
87
88
89
90
91
92



93
94




95
96


















97
98
99
100
101
102
103
104
105

106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139

import re
from config import *
from channels import *
import ahttp
import action


# hook special JSON format in to avoid grepping images by generic handler
action.playlist_fmt_prio.insert(5, "rnjs")
action.playlist_content_map.insert(7, ("rnjs", r'"logo175x175rounded"'))
action.extract_playlist.extr_urls["rnjs"] = dict(
    url   = r" (?x) \"streamUrl\" \s*:\s* \"(\w+:\\?/\\?/[^\"]+)\" ",
    title = r" (?x) \"(?:description|seoTitle)\" \s*:\s* \"([^\"]+)\" ",
    unesc = "json",
)


# Radio.net
#
# · Uses HTML block-wise regex extraction.
#   → <a href="stationname.radio.net"> <img…> <strong>…</strong> <small>…</small>

#



# · There's an API key in each page listing, contained in a script block
#   as `apiKey: '…'?`
#
# · Which is needed for generating the station info JSON urls:
#   → https://api.radio.net/info/v2/search/station?apikey=…&pageindex=1&station=STNAME
#
# · To extract these JSON info targets, a custom extraction recipie is injected
#   into the action module.
#   → "streamUrl": and "description": are scanned for.
#



class radionet (ChannelPlugin):

    # control flags
    has_search = False
    audioformat = "audio/mpeg"
    listformat = "href"
    titles = dict(listeners=False, playing="Description")


    # sources
    apiPrefix = "https://api.radio.net/info/v2"
    genre_url = "http://www.radio.net/genre/{}"
    apiKey = None
    
    
    # Retrieve cat list and map
    def update_categories(self):
        html = ahttp.get("http://www.radio.net/")
        self.set_key(html)
        ls = re.findall("""<li><a class="language-info".*?>([\w\s']+)</a>""", html)
        self.categories = [i for i in ls][0:-18]


    # Fetch entries
    def update_streams(self, cat, search=None):

        # category page, get key

        html = ahttp.get(self.genre_url.format(cat))
        for p in range(2, 4):
            if html.find('"?p={}">'.format(p)) >= 0:
                html += ahttp.get(self.genre_url.format(cat) + "?p={}".format(p))
        self.set_key(html)
        r = []





        # split station blocks




        for row in re.findall("""<div class="stationinfo(.+?)</div>""", html, re.S):
            log.FOR_rOW(1)


















        
            # extract text fields
            d = re.findall("""
              <a\s+href="(?:https?:)?(//(?:[\w-]+)\.radio\.net/s/([^"]+)/?)" .*?
              <img[^>]+ src="([^<">]+)" .*?
              <strong[^>]*>(.*?)</strong> .*?
              <small[^>]*>\s*(.*?)\s*</small>
            """, row, re.X|re.S)
#            log.DATA_ROW(d)

            
            # refurbish extracted strings
            if d and len(d) and len(d[0]) == 5:
                href, name, img, title, desc = d[0]
                r.append(dict(
                    name = name,
                    genre = cat,
                    title = unhtml(title),
                    playing = unhtml(desc),
                    url = "urn:radionet:"+name, #self._url(name),
                    homepage = "http:{}".format(href),
                    img = img,
                ));
        return r

    # api search is gone, now requires to fetch streamUrl from per-radio homepage
    def resolve_urn(self, row):
        if row.get("url", "-").find("urn:radionet:") != 0:
            return
        html = ahttp.get(row["homepage"])
        stream = re.findall('"stream[s:[{"\s]+url"[\s:]+"([^"]+)"', html, re.S|re.I)
        if stream:
            row["url"] = stream[0]
            return row
    

    # extract JavaScript key from any HTML blob (needed for station query)
    def set_key(self, html):
        ls = re.findall("""apiKey: '(\w+)'""", html)
        if ls:
            self.apiKey = ls[0]











|












|
>

>
>
>


<


<




>
>
>







>









|

|
|






>
|

|
|



>
>
>

<
>
>
>
>
|
<
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
|
|
<
<
<
<
<
|
>


<
<
|
|
|
|
|
|
|
|
|











|










28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55

56
57

58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103

104
105
106
107
108

109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129





130
131
132
133


134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163

import re
from config import *
from channels import *
import ahttp
import action


# obsolete: hook special JSON format in to avoid grepping images by generic handler
action.playlist_fmt_prio.insert(5, "rnjs")
action.playlist_content_map.insert(7, ("rnjs", r'"logo175x175rounded"'))
action.extract_playlist.extr_urls["rnjs"] = dict(
    url   = r" (?x) \"streamUrl\" \s*:\s* \"(\w+:\\?/\\?/[^\"]+)\" ",
    title = r" (?x) \"(?:description|seoTitle)\" \s*:\s* \"([^\"]+)\" ",
    unesc = "json",
)


# Radio.net
#
# · Uses HTML block-wise regex extraction.
#   → <div class="sc-1crnfmg-11 sc-1crnfmg-12 cYzyuZ"><a href="/s/kissfmuk">
#   → basically just title/url, images in a separate json blob
#
# · Currently using an urn: to resolve stream urls at play time.
#
# previously:
# · There's an API key in each page listing, contained in a script block
#   as `apiKey: '…'?`

# · Which is needed for generating the station info JSON urls:
#   → https://api.radio.net/info/v2/search/station?apikey=…&pageindex=1&station=STNAME

# · To extract these JSON info targets, a custom extraction recipie is injected
#   into the action module.
#   → "streamUrl": and "description": are scanned for.
#
# todo:
# · https://prod.radio-api.net/stations/local?count=10
#
class radionet (ChannelPlugin):

    # control flags
    has_search = False
    audioformat = "audio/mpeg"
    listformat = "href"
    titles = dict(listeners=False, playing="Description")
    img_resize = 33

    # sources
    apiPrefix = "https://api.radio.net/info/v2"
    genre_url = "http://www.radio.net/genre/{}"
    apiKey = None
    
    
    # Retrieve cat list and map
    def update_categories(self):
        html = ahttp.get("http://www.radio.net/genre")
        self.set_key(html)
        ls = re.findall("""<a class="[^"]+" href="/genre/(\w+)">([^<]+)</a>""", html)
        self.categories = ["Top 40 and Charts"] + [i[1] for i in ls]


    # Fetch entries
    def update_streams(self, cat, search=None):

        # category page, get key
        urlcat = cat.replace(" ", "-").lower()
        html = ahttp.get(self.genre_url.format(urlcat))
        for p in range(2, 4):
            if html.find('?p={}"'.format(p)) >= 0:
                html += ahttp.get(self.genre_url.format(urlcat) + "?p={}".format(p))
        self.set_key(html)
        r = []

        # prefetch images from embedded json (genres and location would also be sourceable from "playables":[…])
        imgs = dict(re.findall('\],"id":"(\w+)","logo100x100":"(htt[^"]+)",', html))
        #log.DATA(imgs)


        # top 100 of the most horrible html serializations
        """
        </div></a></div>
        <div class="sc-1crnfmg-11 sc-1crnfmg-12 cYzyuZ"><a href="/s/kissfmuk">
        <div class="sc-1crnfmg-8 cEmqZI">

        <div class="sc-1crnfmg-0 iDuFwr">
        <div class="lazyload-placeholder"></div>
        <div class="sc-1crnfmg-1 ezaTdn">
        <svg class="sc-1crnfmg-9 hQgRat" xmlns="http://www.w3.org/2000/svg" viewbox="0 0 32 32"><path d="M4 32l25.26-16L4 0z"></path></svg>
        </div>
        </div>
        <div class="sc-1crnfmg-2 incVhC">
        <div class="sc-1crnfmg-3 chXIOx">KISS FM UK</div>
        <div class="sc-1crnfmg-5 fitBQg">London, <!-- -->United Kingdom<!-- --> / Hits, Pop, R'n'B</div>
        <div class="sc-1crnfmg-6 jaxcgd"></div>
        </div>
            {"city":"Hanover","country":"Germany","genres":["Pop","80s","Top 40 & Charts"],"id":"ndr2","logo100x100":"https://d3kle7qwymxpcy.cloudfront.net/images/broadcasts/02/33/2262/1/c100.png","logo300x300":"https://d3kle7qwymxpcy.cloudfront.net/images/broadcasts/02/33/2262/1/c300.png","logo630x630":"","name":"NDR 2","type":"STATION"}')
        """
        rx = re.compile("""
              <a\s+href="(?:https?:)?(?://(?:[\w-]+)\.radio\.net)?/s/([^"]+)/?"> .*?
              <div[^>]+> (\w[^<]+) </div> \s*
              <div[^>]+> (\w[^/]+) \s+ / \s+ (\w.+?)</div> 
            """, re.X|re.S
        )
        # extract text fields
        for d in re.findall(rx, html):





            #log.DATA_ROW(d)
            href, title, location, desc = d
            
            # refurbish extracted strings


            r.append(dict(
                name = href,
                genre = unhtml(desc),
                title = unhtml(title),
                playing = unhtml(location),
                url = "urn:radionet:"+href,
                homepage = "http://www.radio.net/s/{}".format(href),
                img = imgs.get(href, "https://www.radio.net/favicon.ico"),
            ));
        return r

    # api search is gone, now requires to fetch streamUrl from per-radio homepage
    def resolve_urn(self, row):
        if row.get("url", "-").find("urn:radionet:") != 0:
            return
        html = ahttp.get(row["homepage"])
        stream = re.findall('"stream[s:[{"\s]+url"[\s:]+"([^"]+)"', html, re.S|re.I)
        if stream:
            row["url"] = stream[0]
            return row


    # extract JavaScript key from any HTML blob (needed for station query)
    def set_key(self, html):
        ls = re.findall("""apiKey: '(\w+)'""", html)
        if ls:
            self.apiKey = ls[0]