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
|
from bs4 import BeautifulSoup
import feedparser # type: ignore
import time
from datetime import datetime, timezone
from typing import Any
import requests
from app.Item import Item, ItemEnclosure
from app.PluginInterface import Params, PluginInterface
from app.utils import ItemDict, get_config, get_config_or_default
def struct_time_to_utc_datetime(struct_time: time.struct_time) -> datetime:
timestamp = time.mktime(struct_time)
naive_datetime = datetime.fromtimestamp(timestamp)
aware_datetime = naive_datetime.replace(tzinfo=timezone.utc)
return aware_datetime
class Plugin(PluginInterface):
def __init__(self, id: str, params: Params) -> None:
super().__init__(id, params)
self.url: str = get_config(params, "url")
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
)
print(f"[ScraperSourcePlugin#{self.id}] initialized")
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, features="lxml")
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 = link_elem["href"]
if detail_page_url.startswith("/"):
detail_page_url = self.url.strip("/") + detail_page_url
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, features="lxml"
)
guid = detail_page_url
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 guid is None:
guid = f"aggro__{self.id}__{title}"
item = Item(
title=f"{date} – {title}",
link=detail_page_url,
description=description,
pub_date=datetime.now(),
author=author,
category=None,
comments=None,
enclosures=[],
guid=guid,
)
result_items.append(item)
print(
f"[ScraperSourcePlugin#{self.id}] process returns items, n={len(result_items)}"
)
return result_items
|
