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
177
178
179
180
181
182
183
|
# -*- coding: utf-8 -*-
# Copyright 2019 Mike Fährmann
#
# 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.patreon.com/"""
from .common import Extractor, Message
from .. import text
from ..cache import memcache
class PatreonExtractor(Extractor):
"""Base class for patreon extractors"""
category = "patreon"
root = "https://www.patreon.com"
directory_fmt = ("{category}", "{creator[full_name]}")
filename_fmt = "{id}_{title}_{num:>02}.{extension}"
archive_fmt = "{id}_{num}"
_warning = True
def items(self):
yield Message.Version, 1
if self._warning:
if "session_id" not in self.session.cookies:
self.log.warning("no 'session_id' cookie set")
PatreonExtractor._warning = False
for post in self.posts():
yield Message.Directory, post
post["num"] = 0
content = post.get("content")
postfile = post.get("post_file")
for url in text.extract_iter(content or "", 'src="', '"'):
post["num"] += 1
yield Message.Url, url, text.nameext_from_url(url, post)
if postfile:
post["num"] += 1
text.nameext_from_url(postfile["name"], post)
yield Message.Url, postfile["url"], post
for attachment in post["attachments"]:
post["num"] += 1
text.nameext_from_url(attachment["name"], post)
yield Message.Url, attachment["url"], post
def posts(self):
"""Return all relevant post objects"""
def _pagination(self, url):
headers = {"Referer": self.root}
empty = []
while url:
posts = self.request(url, headers=headers).json()
if "included" not in posts:
return
# collect attachments
attachments = {}
for inc in posts["included"]:
if inc["type"] == "attachment":
attachments[inc["id"]] = inc["attributes"]
# update posts
for post in posts["data"]:
attr = post["attributes"]
attr["id"] = text.parse_int(post["id"])
attr["date"] = text.parse_datetime(
attr["published_at"], "%Y-%m-%dT%H:%M:%S.%f%z")
attr["creator"] = self._user(
post["relationships"]["user"]["links"]["related"])
# add attachments to post attributes
files = post["relationships"].get("attachments")
if files:
attr["attachments"] = [
attachments[f["id"]]
for f in files["data"]
]
else:
attr["attachments"] = empty
yield attr
if "links" not in posts:
return
url = posts["links"].get("next")
@memcache(keyarg=1)
def _user(self, url):
user = self.request(url).json()["data"]
attr = user["attributes"]
attr["id"] = user["id"]
attr["date"] = text.parse_datetime(
attr["created"], "%Y-%m-%dT%H:%M:%S.%f%z")
return attr
@staticmethod
def _build_url(endpoint, query):
return (
"https://www.patreon.com/api/" + endpoint +
"?include=user,attachments,user_defined_tags,campaign,poll.choices"
",poll.current_user_responses.user,poll.current_user_responses.cho"
"ice,poll.current_user_responses.poll,access_rules.tier.null"
"&fields[post]=change_visibility_at,comment_count,content,current_"
"user_can_delete,current_user_can_view,current_user_has_liked,embe"
"d,image,is_paid,like_count,min_cents_pledged_to_view,post_file,pu"
"blished_at,patron_count,patreon_url,post_type,pledge_url,thumbnai"
"l_url,teaser_text,title,upgrade_url,url,was_posted_by_campaign_ow"
"ner"
"&fields[user]=image_url,full_name,url"
"&fields[campaign]=avatar_photo_url,earnings_visibility,is_nsfw,is"
"_monthly,name,url"
"&fields[access_rule]=access_rule_type,amount_cents" + query +
"&json-api-use-default-includes=false"
"&json-api-version=1.0"
)
class PatreonCreatorExtractor(PatreonExtractor):
"""Extractor for a creator's works"""
subcategory = "creator"
pattern = (r"(?:https?://)?(?:www\.)?patreon\.com"
r"/(?!(?:home|join|login|signup)(?:$|[/?&#]))([^/?&#]+)/?")
test = ("https://www.patreon.com/koveliana", {
"range": "1-25",
"count": ">= 25",
"keyword": {
"attachments": list,
"comment_count": int,
"content": str,
"creator": dict,
"date": "type:datetime",
"id": int,
"like_count": int,
"post_type": str,
"published_at": str,
"title": str,
},
})
def __init__(self, match):
PatreonExtractor.__init__(self, match)
self.creator = match.group(1).lower()
def posts(self):
url = "{}/{}".format(self.root, self.creator)
page = self.request(url).text
campaign_id = text.extract(page, "/campaign/", "/")[0]
url = self._build_url("posts", (
"&sort=-published_at"
"&filter[is_draft]=false"
"&filter[contains_exclusive_posts]=true"
"&filter[campaign_id]=" + campaign_id
))
return self._pagination(url)
class PatreonUserExtractor(PatreonExtractor):
"""Extractor for media from creators supported by you"""
subcategory = "user"
pattern = r"(?:https?://)?(?:www\.)?patreon\.com/home$"
test = ("https://www.patreon.com/home",)
def posts(self):
url = self._build_url("stream", (
"&page[cursor]=null"
"&filter[is_following]=true"
))
return self._pagination(url)
|
