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
|
#include "feed.hpp"
bool Feed::verify_feed() {
std::string root_name = doc.document_element().name();
SynDomUtils::lower(root_name);
if (root_name == "rss") {
type = FeedType::RSS;
return true;
}
if (root_name == "rdf:rdf") {
type = FeedType::RDF;
return true;
}
if (root_name == "feed") {
type = FeedType::ATOM;
return true;
}
type = FeedType::INVALID;
return false;
}
xml_node Feed::get_feed_node() {
if (type == FeedType::RSS || type == FeedType::RDF) {
return doc.document_element().child("channel");
}
return doc.document_element();
}
void Feed::fix_url(std::string &s) {
SynDomUtils::trim(s);
if (s.empty() || SynDomUtils::is_url(s)) return;
if (SynDomUtils::str_has_prefix(s, "/") && s != url) {
s = url + s;
return;
}
s = "http://" + s;
}
std::string Feed::extract_url() {
std::string res = feed_node.child("link").text().as_string();
if (!res.empty()) return res;
res = SynDomUtils::extract_link(
feed_node, {"alternate"}, {"text/html"}, false, true
);
if (!res.empty()) return res;
res = feed_node.child("id").text().as_string();
if (SynDomUtils::is_url(res)) return res;
return "";
}
std::string Feed::extract_last_update() {
std::string res = SynDomUtils::extract_from_node(
feed_node, __LAST_UPDATE_PARAMS
);
if (!res.empty()) return res;
return SynDomUtils::current_time();
}
std::string Feed::extract_img_url() {
return SynDomUtils::extract_from_node(
feed_node, __IMG_URL_PARAMS
);
}
std::string Feed::extract_rss_url() {
return SynDomUtils::extract_link(
feed_node,
{"self"}, {"application/rss+xml", "application/atom+xml"},
false, true
);
}
void Feed::extract_feed_data() {
feed_node = get_feed_node();
// title
// simple enough to be done raw
title = (feed_node.child("title").text().as_string());
SynDomUtils::trim(title);
// description
description = SynDomUtils::extract_from_node(
feed_node, __DESCRIPTION_PARAMS
);
// url, as in the website link relative to the feed
url = extract_url();
fix_url(url);
// last_update
last_update = extract_last_update();
// img_url
img_url = extract_img_url();
fix_url(img_url);
// rss_url
rss_url = extract_rss_url();
fix_url(rss_url);
}
void Feed::extract_feed_items() {
if (type == FeedType::RDF) {
xml_node item = feed_node.child("items").child("rdf:Seq").child(
"rdf:li"
);
while (item) {
std::string url = item.attribute("rdf:resource").value();
xml_node item_info = doc.document_element()
.find_child_by_attribute("item", "rdf:about", url.c_str());
if (item_info) {
feed_items.push_back(FeedItem(item_info, url));
}
item = item.next_sibling("rdf:li");
}
return;
}
std::string item_tag = "item";
xml_node first_item = feed_node.child(item_tag.c_str());
if (!first_item) {
item_tag = "entry";
first_item = feed_node.child(item_tag.c_str());
}
if (!first_item) return;
xml_node item = first_item;
while (item) {
feed_items.push_back(FeedItem(item, url));
item = item.next_sibling(item_tag.c_str());
}
}
void Feed::parse() {
xml_parse_result res = doc.load_file(path.c_str());
if (!res) {
throw std::runtime_error("Error parsing XML file: "+path);
}
if (!verify_feed()) {
throw std::runtime_error(
"Error: the XML file provided is not a feed: "+path
);
}
extract_feed_data();
extract_feed_items();
}
std::string Feed::to_json(bool no_items) {
std::string res = "\n{\n"
" \"title\": \"" + title + "\",\n"
" \"description\": \"" + description + "\",\n"
" \"url\": \"" + url + "\",\n"
" \"last_update\": \"" + last_update + "\",\n"
" \"img_url\": \"" + img_url + "\",\n"
" \"rss_url\": \"" + rss_url;
if (!no_items) {
res += "\",\n \"items\": [\n";
for (auto fi: feed_items) {
res += fi.to_json() + ",\n";
}
res = res.substr(0, res.size()-2) + "\n";
res += " ]\n}\n";
}
else {
res += "\n}\n";
}
return res;
}
|