1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
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
164
165
166
167
168
169
170
171
172
173
174
175
176
|
# -*- coding: utf-8 -*-
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://www.bilibili.com/"""
from .common import Extractor, Message
from .. import text, util, exception
class BilibiliExtractor(Extractor):
"""Base class for bilibili extractors"""
category = "bilibili"
root = "https://www.bilibili.com"
request_interval = (3.0, 6.0)
def _init(self):
self.api = BilibiliAPI(self)
def items(self):
for article in self.articles():
article["_extractor"] = BilibiliArticleExtractor
url = f"{self.root}/opus/{article['opus_id']}"
yield Message.Queue, url, article
def articles(self):
return ()
class BilibiliArticleExtractor(BilibiliExtractor):
"""Extractor for a bilibili article"""
subcategory = "article"
pattern = (r"(?:https?://)?"
r"(?:t\.bilibili\.com|(?:www\.)?bilibili.com/opus)/(\d+)")
example = "https://www.bilibili.com/opus/12345"
directory_fmt = ("{category}", "{username}")
filename_fmt = "{id}_{num}.{extension}"
archive_fmt = "{id}_{num}"
def items(self):
article_id = self.groups[0]
article = self.api.article(article_id)
# Flatten modules list
modules = {}
for module in article["detail"]["modules"]:
if module["module_type"] == "MODULE_TYPE_BLOCKED":
self.log.warning("%s: Blocked Article\n%s", article_id,
module["module_blocked"].get("hint_message"))
del module["module_type"]
modules.update(module)
article["detail"]["modules"] = modules
article["username"] = modules["module_author"]["name"]
pics = []
if "module_top" in modules:
try:
pics.extend(modules["module_top"]["display"]["album"]["pics"])
except Exception:
pass
if "module_content" in modules:
for paragraph in modules["module_content"]["paragraphs"]:
if "pic" not in paragraph:
continue
try:
pics.extend(paragraph["pic"]["pics"])
except Exception:
pass
article["count"] = len(pics)
yield Message.Directory, "", article
for article["num"], pic in enumerate(pics, 1):
url = pic["url"]
article.update(pic)
yield Message.Url, url, text.nameext_from_url(url, article)
class BilibiliUserArticlesExtractor(BilibiliExtractor):
"""Extractor for a bilibili user's articles"""
subcategory = "user-articles"
pattern = (r"(?:https?://)?space\.bilibili\.com/(\d+)"
r"/(?:article|upload/opus)")
example = "https://space.bilibili.com/12345/article"
def articles(self):
return self.api.user_articles(self.groups[0])
class BilibiliUserArticlesFavoriteExtractor(BilibiliExtractor):
subcategory = "user-articles-favorite"
pattern = (r"(?:https?://)?space\.bilibili\.com"
r"/(\d+)/favlist\?fid=opus")
example = "https://space.bilibili.com/12345/favlist?fid=opus"
_warning = True
def articles(self):
if self._warning:
if not self.cookies_check(("SESSDATA",)):
self.log.error("'SESSDATA' cookie required")
BilibiliUserArticlesFavoriteExtractor._warning = False
return self.api.user_favlist()
class BilibiliAPI():
def __init__(self, extractor):
self.extractor = extractor
def _call(self, endpoint, params):
url = "https://api.bilibili.com/x/polymer/web-dynamic/v1" + endpoint
data = self.extractor.request_json(url, params=params)
if data["code"]:
self.extractor.log.debug("Server response: %s", data)
raise exception.AbortExtraction("API request failed")
return data
def user_articles(self, user_id):
endpoint = "/opus/feed/space"
params = {"host_mid": user_id}
while True:
data = self._call(endpoint, params)
for item in data["data"]["items"]:
params["offset"] = item["opus_id"]
yield item
if not data["data"]["has_more"]:
break
def article(self, article_id):
url = "https://www.bilibili.com/opus/" + article_id
while True:
page = self.extractor.request(url).text
try:
return util.json_loads(text.extr(
page, "window.__INITIAL_STATE__=", "};") + "}")
except Exception:
if "window._riskdata_" not in page:
raise exception.AbortExtraction(
article_id + ": Unable to extract INITIAL_STATE data")
self.extractor.wait(seconds=300)
def user_favlist(self):
endpoint = "/opus/feed/fav"
params = {"page": 1, "page_size": 20}
while True:
data = self._call(endpoint, params)["data"]
yield from data["items"]
if not data.get("has_more"):
break
params["page"] += 1
def login_user_id(self):
url = "https://api.bilibili.com/x/space/v2/myinfo"
data = self.extractor.request_json(url)
if data["code"] != 0:
self.extractor.log.debug("Server response: %s", data)
raise exception.AbortExtraction(
"API request failed. Are you logges in?")
try:
return data["data"]["profile"]["mid"]
except Exception:
raise exception.AbortExtraction("API request failed")
|
