fmscrape 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of fmscrape might be problematic. Click here for more details.

@@ -0,0 +1,207 @@
1
+ """Parsers for Last.fm tag pages (/tag/<tag>, /artists, /albums, /tracks)."""
2
+
3
+ from __future__ import annotations
4
+
5
+ from bs4 import BeautifulSoup
6
+
7
+ from fmscrape.errors import ParseError
8
+ from fmscrape.models import (
9
+ AlbumEntry,
10
+ AlbumListPage,
11
+ ArtistEntry,
12
+ ArtistListPage,
13
+ ArtistRef,
14
+ PaginationAttr,
15
+ TagDetails,
16
+ TagsListResult,
17
+ TrackEntry,
18
+ TrackListPage,
19
+ )
20
+ from fmscrape.normalize import absolute_url, parse_int
21
+ from fmscrape.parsers.common import (
22
+ images_from_element,
23
+ parse_pagination_total,
24
+ parse_tags,
25
+ parse_wiki,
26
+ )
27
+
28
+ ARTIST_ITEM_SELECTOR = ".big-artist-list-item"
29
+ ALBUM_ITEM_SELECTOR = ".resource-list--release-list-item"
30
+ TRACK_ROW_SELECTOR = "tr.chartlist-row:not(.chartlist__placeholder-row)"
31
+
32
+
33
+ def parse_tag_info(html: str, *, url: str, tag: str) -> TagDetails:
34
+ soup = BeautifulSoup(html, "lxml")
35
+ if soup.select_one("h1") is None:
36
+ raise ParseError("Tag page invalid", url=url, selector="h1")
37
+ return TagDetails(
38
+ name=tag,
39
+ url=url,
40
+ wiki=parse_wiki(soup),
41
+ )
42
+
43
+
44
+ def parse_tag_similar(html: str, *, url: str) -> TagsListResult:
45
+ soup = BeautifulSoup(html, "lxml")
46
+ if soup.select_one("h1") is None:
47
+ raise ParseError("Tag page invalid", url=url, selector="h1")
48
+ return TagsListResult(tags=parse_tags(soup), root_key="similartags")
49
+
50
+
51
+ def parse_tag_top_artists(
52
+ html: str,
53
+ *,
54
+ url: str,
55
+ tag: str,
56
+ page: int = 1,
57
+ limit: int | None = None,
58
+ ) -> ArtistListPage:
59
+ soup = BeautifulSoup(html, "lxml")
60
+ items = soup.select(ARTIST_ITEM_SELECTOR)
61
+ if not items and soup.select_one("h1") is None:
62
+ raise ParseError("Tag top artists not found", url=url, selector=ARTIST_ITEM_SELECTOR)
63
+
64
+ artists: list[ArtistEntry] = []
65
+ for idx, item in enumerate(items, start=1):
66
+ link = item.select_one("h3.big-artist-list-title a, a.link-block-target")
67
+ if link is None:
68
+ continue
69
+ href = link.get("href")
70
+ listeners_el = item.select_one(".big-artist-list-listeners")
71
+ listeners = parse_int(listeners_el.get_text(strip=True) if listeners_el else None)
72
+ artists.append(
73
+ ArtistEntry(
74
+ name=link.get_text(strip=True),
75
+ url=absolute_url(href if isinstance(href, str) else ""),
76
+ images=images_from_element(item),
77
+ listeners=listeners,
78
+ rank=(page - 1) * 20 + idx,
79
+ )
80
+ )
81
+
82
+ if limit is not None and limit >= 0:
83
+ artists = artists[:limit]
84
+
85
+ total_pages = parse_pagination_total(soup, page)
86
+ per_page = limit if limit is not None else max(len(artists), 1)
87
+ return ArtistListPage(
88
+ artists=artists,
89
+ attr=PaginationAttr(
90
+ page=page,
91
+ per_page=per_page,
92
+ total_pages=total_pages,
93
+ total=total_pages * per_page,
94
+ tag=tag,
95
+ ),
96
+ root_key="topartists",
97
+ )
98
+
99
+
100
+ def parse_tag_top_albums(
101
+ html: str,
102
+ *,
103
+ url: str,
104
+ tag: str,
105
+ page: int = 1,
106
+ limit: int | None = None,
107
+ ) -> AlbumListPage:
108
+ soup = BeautifulSoup(html, "lxml")
109
+ items = soup.select(ALBUM_ITEM_SELECTOR)
110
+ if not items and soup.select_one("h1") is None:
111
+ raise ParseError("Tag top albums not found", url=url, selector=ALBUM_ITEM_SELECTOR)
112
+
113
+ albums: list[AlbumEntry] = []
114
+ for idx, item in enumerate(items, start=1):
115
+ link = item.select_one("h3.resource-list--release-list-item-name a")
116
+ if link is None:
117
+ continue
118
+ href = link.get("href")
119
+ artist_el = item.select_one(".resource-list--release-list-item-artist a")
120
+ ahref = artist_el.get("href") if artist_el else None
121
+ listeners_el = item.select_one(".resource-list--release-list-item-listeners")
122
+ listeners = parse_int(listeners_el.get_text(strip=True) if listeners_el else None)
123
+ albums.append(
124
+ AlbumEntry(
125
+ name=link.get_text(strip=True),
126
+ artist=ArtistRef(
127
+ name=artist_el.get_text(strip=True) if artist_el else "",
128
+ url=absolute_url(ahref if isinstance(ahref, str) else ""),
129
+ ),
130
+ url=absolute_url(href if isinstance(href, str) else ""),
131
+ images=images_from_element(item),
132
+ listeners=listeners,
133
+ rank=(page - 1) * 20 + idx,
134
+ )
135
+ )
136
+
137
+ if limit is not None and limit >= 0:
138
+ albums = albums[:limit]
139
+
140
+ total_pages = parse_pagination_total(soup, page)
141
+ per_page = limit if limit is not None else max(len(albums), 1)
142
+ return AlbumListPage(
143
+ albums=albums,
144
+ attr=PaginationAttr(
145
+ page=page,
146
+ per_page=per_page,
147
+ total_pages=total_pages,
148
+ total=total_pages * per_page,
149
+ tag=tag,
150
+ ),
151
+ root_key="albums",
152
+ )
153
+
154
+
155
+ def parse_tag_top_tracks(
156
+ html: str,
157
+ *,
158
+ url: str,
159
+ tag: str,
160
+ page: int = 1,
161
+ limit: int | None = None,
162
+ ) -> TrackListPage:
163
+ soup = BeautifulSoup(html, "lxml")
164
+ rows = soup.select(TRACK_ROW_SELECTOR)
165
+ if not rows and soup.select_one("h1") is None:
166
+ raise ParseError("Tag top tracks not found", url=url, selector=TRACK_ROW_SELECTOR)
167
+
168
+ tracks: list[TrackEntry] = []
169
+ for idx, row in enumerate(rows, start=1):
170
+ name_el = row.select_one("td.chartlist-name a")
171
+ if name_el is None:
172
+ continue
173
+ href = name_el.get("href")
174
+ artist_el = row.select_one("td.chartlist-artist a")
175
+ ahref = artist_el.get("href") if artist_el else None
176
+ rank_el = row.select_one("td.chartlist-index")
177
+ rank = parse_int(rank_el.get_text(strip=True) if rank_el else None) or ((page - 1) * 50 + idx)
178
+ tracks.append(
179
+ TrackEntry(
180
+ name=name_el.get_text(strip=True),
181
+ artist=ArtistRef(
182
+ name=artist_el.get_text(strip=True) if artist_el else "",
183
+ url=absolute_url(ahref if isinstance(ahref, str) else ""),
184
+ ),
185
+ url=absolute_url(href if isinstance(href, str) else ""),
186
+ images=images_from_element(row),
187
+ rank=rank,
188
+ )
189
+ )
190
+
191
+ if limit is not None and limit >= 0:
192
+ tracks = tracks[:limit]
193
+
194
+ total_pages = parse_pagination_total(soup, page)
195
+ per_page = limit if limit is not None else 50
196
+ return TrackListPage(
197
+ tracks=tracks,
198
+ attr=PaginationAttr(
199
+ page=page,
200
+ per_page=per_page,
201
+ total_pages=total_pages,
202
+ total=total_pages * per_page,
203
+ tag=tag,
204
+ ),
205
+ root_key="tracks",
206
+ )
207
+
@@ -0,0 +1,184 @@
1
+ """Parsers for Last.fm track pages (/music/<artist>/_/<track>, +tags, search)."""
2
+
3
+ from __future__ import annotations
4
+
5
+ from bs4 import BeautifulSoup
6
+
7
+ from fmscrape.errors import ParseError
8
+ from fmscrape.models import (
9
+ AlbumRef,
10
+ ArtistRef,
11
+ PaginationAttr,
12
+ SearchResultsPage,
13
+ TagsListResult,
14
+ TrackEntry,
15
+ TrackInfo,
16
+ TrackListPage,
17
+ )
18
+ from fmscrape.normalize import absolute_url
19
+ from fmscrape.parsers.common import (
20
+ images_from_element,
21
+ parse_duration_ms,
22
+ parse_pagination_total,
23
+ parse_stats_intabbr,
24
+ parse_tags,
25
+ parse_wiki,
26
+ )
27
+
28
+ HEADER_TITLE_SELECTOR = "h1.header-new-title, h1.header-title, h1"
29
+ HEADER_ARTIST_SELECTOR = ".header-new-crumb a, .header-title-secondary a"
30
+ SIMILAR_TRACK_SELECTOR = ".track-similar-tracks-item, .similar-tracks-item"
31
+ SEARCH_ROW_SELECTOR = "tr.chartlist-row:not(.chartlist__placeholder-row)"
32
+
33
+
34
+ def parse_track_info(html: str, *, url: str) -> TrackInfo:
35
+ soup = BeautifulSoup(html, "lxml")
36
+ title_el = soup.select_one(HEADER_TITLE_SELECTOR)
37
+ if title_el is None:
38
+ raise ParseError("Track title not found", url=url, selector=HEADER_TITLE_SELECTOR)
39
+ name = title_el.get_text(strip=True)
40
+
41
+ artist_el = soup.select_one(HEADER_ARTIST_SELECTOR)
42
+ artist_name = artist_el.get_text(strip=True) if artist_el else ""
43
+ artist_href = artist_el.get("href") if artist_el else None
44
+
45
+ canonical_el = soup.select_one('link[rel="canonical"]')
46
+ canonical_href = canonical_el.get("href") if canonical_el else None
47
+ canonical_url = canonical_href if isinstance(canonical_href, str) and canonical_href else url
48
+
49
+ stats = parse_stats_intabbr(soup)
50
+ tags = parse_tags(soup)
51
+ wiki = parse_wiki(soup)
52
+
53
+ duration_ms = 0
54
+ for dt, dd in zip(
55
+ soup.select(".catalogue-metadata-heading"),
56
+ soup.select(".catalogue-metadata-description"),
57
+ ):
58
+ if "length" in dt.get_text(strip=True).lower():
59
+ duration_ms = parse_duration_ms(dd.get_text(strip=True))
60
+ break
61
+
62
+ album_ref: AlbumRef | None = None
63
+ album_el = soup.select_one(".featured-item-heading a, .source-album-name a")
64
+ if album_el is not None:
65
+ ahref = album_el.get("href")
66
+ album_ref = AlbumRef(
67
+ name=album_el.get_text(strip=True),
68
+ url=absolute_url(ahref if isinstance(ahref, str) else ""),
69
+ )
70
+
71
+ return TrackInfo(
72
+ name=name,
73
+ artist=ArtistRef(
74
+ name=artist_name,
75
+ url=absolute_url(artist_href if isinstance(artist_href, str) else ""),
76
+ ),
77
+ url=canonical_url,
78
+ duration=duration_ms,
79
+ listeners=stats.listeners,
80
+ playcount=stats.playcount,
81
+ album=album_ref,
82
+ toptags=tags,
83
+ wiki=wiki,
84
+ )
85
+
86
+
87
+ def parse_track_similar(
88
+ html: str,
89
+ *,
90
+ url: str,
91
+ artist: str,
92
+ limit: int | None = None,
93
+ ) -> TrackListPage:
94
+ soup = BeautifulSoup(html, "lxml")
95
+ if soup.select_one(HEADER_TITLE_SELECTOR) is None:
96
+ raise ParseError("Track page invalid", url=url, selector=HEADER_TITLE_SELECTOR)
97
+
98
+ tracks: list[TrackEntry] = []
99
+ for idx, item in enumerate(soup.select(SIMILAR_TRACK_SELECTOR), start=1):
100
+ name_el = item.select_one(".track-similar-tracks-item-name a, .similar-tracks-item-name a, h3 a")
101
+ if name_el is None:
102
+ continue
103
+ href = name_el.get("href")
104
+ artist_el = item.select_one(".track-similar-tracks-item-artist a, .similar-tracks-item-artist a")
105
+ ahref = artist_el.get("href") if artist_el else None
106
+ tracks.append(
107
+ TrackEntry(
108
+ name=name_el.get_text(strip=True),
109
+ artist=ArtistRef(
110
+ name=artist_el.get_text(strip=True) if artist_el else artist,
111
+ url=absolute_url(ahref if isinstance(ahref, str) else ""),
112
+ ),
113
+ url=absolute_url(href if isinstance(href, str) else ""),
114
+ images=images_from_element(item),
115
+ rank=idx,
116
+ )
117
+ )
118
+
119
+ if limit is not None and limit >= 0:
120
+ tracks = tracks[:limit]
121
+
122
+ return TrackListPage(
123
+ tracks=tracks,
124
+ attr=PaginationAttr(page=1, per_page=len(tracks) or 1, total_pages=1, total=len(tracks), artist=artist),
125
+ root_key="similartracks",
126
+ )
127
+
128
+
129
+ def parse_track_top_tags(html: str, *, url: str) -> TagsListResult:
130
+ soup = BeautifulSoup(html, "lxml")
131
+ if soup.select_one("h1") is None:
132
+ raise ParseError("Track tags page invalid", url=url, selector="h1")
133
+ return TagsListResult(tags=parse_tags(soup), root_key="toptags")
134
+
135
+
136
+ def parse_track_search(
137
+ html: str,
138
+ *,
139
+ url: str,
140
+ page: int = 1,
141
+ limit: int | None = None,
142
+ ) -> SearchResultsPage:
143
+ soup = BeautifulSoup(html, "lxml")
144
+ rows = soup.select(SEARCH_ROW_SELECTOR)
145
+ if not rows and soup.select_one("h1, .search-results") is None:
146
+ raise ParseError("Track search results not found", url=url, selector=SEARCH_ROW_SELECTOR)
147
+
148
+ tracks: list[TrackEntry] = []
149
+ for row in rows:
150
+ name_el = row.select_one("td.chartlist-name a")
151
+ if name_el is None:
152
+ continue
153
+ href = name_el.get("href")
154
+ artist_el = row.select_one("td.chartlist-artist a")
155
+ ahref = artist_el.get("href") if artist_el else None
156
+ tracks.append(
157
+ TrackEntry(
158
+ name=name_el.get_text(strip=True),
159
+ artist=ArtistRef(
160
+ name=artist_el.get_text(strip=True) if artist_el else "",
161
+ url=absolute_url(ahref if isinstance(ahref, str) else ""),
162
+ ),
163
+ url=absolute_url(href if isinstance(href, str) else ""),
164
+ images=images_from_element(row),
165
+ )
166
+ )
167
+
168
+ if limit is not None and limit >= 0:
169
+ tracks = tracks[:limit]
170
+
171
+ total_pages = parse_pagination_total(soup, page)
172
+ per_page = limit if limit is not None else 30
173
+ return SearchResultsPage(
174
+ items=tracks,
175
+ attr=PaginationAttr(
176
+ page=page,
177
+ per_page=per_page,
178
+ total_pages=total_pages,
179
+ total=total_pages * per_page,
180
+ ),
181
+ match_key="trackmatches",
182
+ item_key="track",
183
+ )
184
+