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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
|
from bs4 import BeautifulSoup
import time
import hashlib
from datetime import datetime, timezone
from typing import Any
import re
import requests
from app.Item import Item, ItemEnclosure, ItemGUID, ItemMediaContent
from app.PluginInterface import Params, PluginInterface
from app.utils import ItemDict, get_config, get_config_or_default
class Plugin(PluginInterface):
def __init__(self, id: str, params: Params) -> None:
super().__init__(id, params)
self.url: str = get_config(params, "url").strip("/")
self.selector_post: str = get_config(params, "selector_post")
self.selector_title: str | None = get_config_or_default(
params, "selector_title", None
)
self.selector_date: str | None = get_config_or_default(
params, "selector_date", None
)
self.selector_link: str | None = get_config_or_default(
params, "selector_link", None
)
self.selector_description: str | None = get_config_or_default(
params, "selector_description", None
)
self.selector_author: str | None = get_config_or_default(
params, "selector_author", None
)
self.selector_image: str | None = get_config_or_default(
params, "selector_image", None
)
self.show_image_in_description: bool = get_config_or_default(
params, "show_image_in_description", True
)
print(f"[ScraperSourcePlugin#{self.id}] initialized")
def absolute_link(self, link: str) -> str:
if link.startswith("/") or link.startswith("#"):
link = self.url + link
return link
def process(self, source_id: str | None, items: list[Item]) -> list[Item]:
print(f"[ScraperSourcePlugin#{self.id}] process called")
result_items: list[Item] = []
with requests.session() as session:
page_resp = session.get(self.url, allow_redirects=True)
page_elem = BeautifulSoup(page_resp.text, "html.parser")
post_elems = eval(self.selector_post, {"page": page_elem})
for post_elem in post_elems:
if self.selector_link:
link_elem = eval(
self.selector_link, {"page": page_elem, "post": post_elem}
)[0]
detail_page_url = self.absolute_link(link_elem["href"])
else:
detail_page_url = None
if detail_page_url:
detail_page_resp = session.get(
detail_page_url, allow_redirects=True
)
detail_page_elem = BeautifulSoup(
detail_page_resp.text, "html.parser"
)
guid = ItemGUID(detail_page_url, is_perma_link=True)
else:
detail_page_elem = None
guid = None
if self.selector_title:
title_elem = eval(
self.selector_title,
{
"page": page_elem,
"post": post_elem,
"detail_page": detail_page_elem,
},
)[0]
title = title_elem.get_text().strip()
else:
title = None
if self.selector_description:
description_elem = eval(
self.selector_description,
{
"page": page_elem,
"post": post_elem,
"detail_page": detail_page_elem,
},
)[0]
description = str(description_elem).strip()
else:
description = None
if self.selector_date:
date_elem = eval(
self.selector_date,
{
"page": page_elem,
"post": post_elem,
"detail_page": detail_page_elem,
},
)[0]
date = date_elem.get_text().strip()
else:
date = None
if self.selector_author:
author_elem = eval(
self.selector_author,
{
"page": page_elem,
"post": post_elem,
"detail_page": detail_page_elem,
},
)[0]
author = author_elem.get_text().strip()
else:
author = None
if self.selector_image:
image_elem = eval(
self.selector_image,
{
"page": page_elem,
"post": post_elem,
"detail_page": detail_page_elem,
},
)[0]
if image_elem.has_attr("src"):
image_src = image_elem["src"]
elif image_elem.has_attr("href"):
image_src = image_elem["href"]
elif (
image_elem.has_attr("style")
and "background-image:" in image_elem["style"]
):
match = re.match(
r"background-image:\s*url\((?P<url>.*?)\)",
image_elem["style"],
)
if match is None:
raise Exception(
f"[ScraperSourcePlugin#{self.id}] weird regex result when looking for background-image"
)
image_src = match.group("url")
else:
image_src = None
else:
image_src = None
if guid is None:
if title:
guid = ItemGUID(f"aggro__{self.id}__{title}")
elif description:
digest = str(hashlib.sha256(description.encode("utf-8")))
guid = ItemGUID(f"aggro__{self.id}__{digest[:32]}")
else:
raise Exception(
f"[ScraperSourcePlugin#{self.id}] both title and description are None"
)
if image_src is not None:
image_src = self.absolute_link(image_src)
image_html = f'<img src="{image_src}"><br><br>'
if description and self.show_image_in_description:
description = image_html + description
elif description is None:
description = image_html
media_content = ItemMediaContent(
url=image_src,
medium="image",
)
else:
media_content = None
if description:
description = description.replace('src="/', f'src="{self.url}/')
description = description.replace('src="#', f'src="{self.url}#')
description = description.replace('href="/', f'href="{self.url}/')
description = description.replace('href="#', f'href="{self.url}#')
item = Item(
title=f"{date} – {title}",
link=detail_page_url if detail_page_url else self.url,
description=description,
pub_date=None, # TODO pub_date parsing
author=author,
category=None,
comments=None,
enclosures=[],
guid=guid,
media_content=media_content,
)
result_items.append(item)
print(
f"[ScraperSourcePlugin#{self.id}] process returns items, n={len(result_items)}"
)
return result_items
|
