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

⌈⌋ ⎇ branch:  streamtuner2


Check-in [4eccc8b70a]

Overview
Comment:Implement search function for I-R, fix DOM extraction method.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 4eccc8b70a9e6903f803f05cd19aeec2cc8f297b
User & Date: mario on 2016-12-26 21:54:10
Other Links: manifest | tags
Context
2016-12-27
21:20
Remove stale comment, fix whitespace issue check-in: b5753830fa user: mario tags: trunk
2016-12-26
21:54
Implement search function for I-R, fix DOM extraction method. check-in: 4eccc8b70a user: mario tags: trunk
20:43
Use file:/// urls again. Escape backslashes for Windows now. check-in: 9bef9860b6 user: Oliver tags: trunk
Changes

Modified channels/internet_radio.py from [e2da369cc7] to [78008b144e].

1
2
3
4
5
6
7
8
9
10
11
12
13
14
# api: streamtuner2
# title: Internet-Radio
# description: Broad list of webradios from all genres.
# type: channel
# category: radio
# version: 1.2
# url: http://www.internet-radio.org.uk/
# config:
#    { name: internetradio_max_pages,  type: int,  value: 5,  category: limit,  description: How many pages to fetch and read. }
# priority: standard
# png:
#   iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAABHNCSVQICAgIfAhkiAAAAaZJREFUOI2N0j1PlEEUBeBnlsVoRJcCPwINxIJGAoWVFbVK4g8w
#   oUUTFRNbG3+FhVErK36BhcYCrTR8FS4mRGUXFEKCUizRwLXgnfV1Awk3mUzmnHPvPXNnUkSE40RKFYxhHKMYxFb1GIlnMLVN/etBUjuGWDm6wEHHyQbLW/Qd
#   JTu8QEq9mJlnogz3sHOJV3iHz2iKzuDiH+bm+J3XD74EU5Gc7pSn/4aYUi14s8BIhkZ5puKhvdgpNFVccaA5oaP7TO66SCuYKnG9weMmjaz5yadqqfvkPE/z





|
|







1
2
3
4
5
6
7
8
9
10
11
12
13
14
# api: streamtuner2
# title: Internet-Radio
# description: Broad list of webradios from all genres.
# type: channel
# category: radio
# version: 1.5
# url: http://www.internet-radio.com/
# config:
#    { name: internetradio_max_pages,  type: int,  value: 5,  category: limit,  description: How many pages to fetch and read. }
# priority: standard
# png:
#   iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAABHNCSVQICAgIfAhkiAAAAaZJREFUOI2N0j1PlEEUBeBnlsVoRJcCPwINxIJGAoWVFbVK4g8w
#   oUUTFRNbG3+FhVErK36BhcYCrTR8FS4mRGUXFEKCUizRwLXgnfV1Awk3mUzmnHPvPXNnUkSE40RKFYxhHKMYxFb1GIlnMLVN/etBUjuGWDm6wEHHyQbLW/Qd
#   JTu8QEq9mJlnogz3sHOJV3iHz2iKzuDiH+bm+J3XD74EU5Gc7pSn/4aYUi14s8BIhkZ5puKhvdgpNFVccaA5oaP7TO66SCuYKnG9weMmjaz5yadqqfvkPE/z
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
# streams and gui
class internet_radio (ChannelPlugin):

    # control data
    listformat = "pls"
    categories = []
    base_url = "https://www.internet-radio.com/"



    # load genres
    def update_categories(self):
    
        html = ahttp.get(self.base_url)
        rx = re.compile("""="/stations/[-+&.\w\s%]+/">([^<]+)<""")
        cats = rx.findall(html)
        cats = list(set(cats))
        cats = [s.capitalize() for s in cats]
        self.categories = sorted(list(set(cats)))


    # fetch station lists
    def update_streams(self, cat):
    
        entries = []
        if cat not in self.categories:
            return []

        rx_pages = re.compile('href="/stations/[-+\w%\d\s]+/page(\d+)">\d+</a>')

        # Fetch multiple pages at once
        html = []
        max_pages = max(int(conf.internetradio_max_pages), 1)
        for page in range(1, max_pages):
        
            # Append HTML source

            html.append(
                ahttp.get(
                    self.base_url + "stations/" +
                    cat.lower().replace(" ", "%20") +
                    "/" + ("page"+str(page) if page>1 else "")
                )



            )

            # Is there a next page?
            if str(page+1) not in rx_pages.findall(html[-1]):
                break
            self.parent.status(float(page)/float(max_pages+1), timeout=1)

        # Alternatively try regex or pyquery parsing







>














|


|










>
|
|
<
<
<

>
>
>
|







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
# streams and gui
class internet_radio (ChannelPlugin):

    # control data
    listformat = "pls"
    categories = []
    base_url = "https://www.internet-radio.com/"
    has_search = True


    # load genres
    def update_categories(self):
    
        html = ahttp.get(self.base_url)
        rx = re.compile("""="/stations/[-+&.\w\s%]+/">([^<]+)<""")
        cats = rx.findall(html)
        cats = list(set(cats))
        cats = [s.capitalize() for s in cats]
        self.categories = sorted(list(set(cats)))


    # fetch station lists
    def update_streams(self, cat, search=None):
    
        entries = []
        if not search and cat not in self.categories:
            return []

        rx_pages = re.compile('href="/stations/[-+\w%\d\s]+/page(\d+)">\d+</a>')

        # Fetch multiple pages at once
        html = []
        max_pages = max(int(conf.internetradio_max_pages), 1)
        for page in range(1, max_pages):
        
            # Append HTML source
            if search:
                html.append(
                    ahttp.get("%ssearch/?radio=%s%s" % (self.base_url, search, "&page=%s" % page if page>1 else ""))



                )
            else:
                html.append(
                    ahttp.get("%sstations/%s/%s" % (self.base_url, cat.lower().replace(" ", "%20"), "page%s" % page if page>1 else ""))
                )

            # Is there a next page?
            if str(page+1) not in rx_pages.findall(html[-1]):
                break
            self.parent.status(float(page)/float(max_pages+1), timeout=1)

        # Alternatively try regex or pyquery parsing
148
149
150
151
152
153
154

155
156
157

158


159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180



181
182
183
184
        log.PROC("internet-radio, dom")
        rx_numbers = re.compile("(\d+)")
        r = []
        for html in html_list:
            # the streams are arranged in table rows
            doc = pq(html)
            for dir in (pq(e) for e in doc("tr")):

                
                # bitrate/listeners
                bl = dir.find("p").text()

                bl = rx_numbers.findall(str(bl) + " 0 0")


                
                # stream url
                url = dir.find("i").eq(0).attr("onclick")
                if url:
                    url = re.search("(http://[^\'\"\>]+)", url)
                    if url:
                        url = url.group(0)
                    else:
                        url = ""
                else:
                    url = ""
                
                r.append({
                    "title": dir.find("h4").text(),
                    "homepage": ahttp.fix_url(dir.find("a.small").attr("href")),
                    "url": url,
                    "genre": dir.find("a[href^='/stations/']").text(),
                    "listeners": int(bl[0]),
                    "bitrate": int(bl[1]),
                    "format": "audio/mpeg",
                    "playing": dir.find("b").text(),
                })



        return r
            









>


|
>
|
>
>


|









|

|

|




<
>
>
>




150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185

186
187
188
189
190
191
192
        log.PROC("internet-radio, dom")
        rx_numbers = re.compile("(\d+)")
        r = []
        for html in html_list:
            # the streams are arranged in table rows
            doc = pq(html)
            for dir in (pq(e) for e in doc("tr")):
                #log.HTML(dir)
                
                # bitrate/listeners
                bl = dir.find("p")
                if bl:
                    bl = rx_numbers.findall(str(bl.text()) + " 0 0")
                else:
                    bl = [0, 0]
                
                # stream url
                url = dir.find("i").eq(0).parent().attr("onclick")
                if url:
                    url = re.search("(http://[^\'\"\>]+)", url)
                    if url:
                        url = url.group(0)
                    else:
                        url = ""
                else:
                    url = ""
                
                row = {
                    "title": dir.find("h4").text(),
                    "homepage": ahttp.fix_url(dir.find("a.small").attr("href") or ""),
                    "url": url,
                    "genre": dir.find("a[href^='/stations/']").text() or "",
                    "listeners": int(bl[0]),
                    "bitrate": int(bl[1]),
                    "format": "audio/mpeg",
                    "playing": dir.find("b").text(),

                }
                #log.DATA(row)
                r.append(row)
        return r