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
|
/* rsspp - Copyright (C) 2008-2009 Andreas Krennmair <ak@newsbeuter.org>
* Licensed under the MIT/X Consortium License. See file LICENSE
* for more information.
*/
#include <config.h>
#include <rsspp_internal.h>
#include <utils.h>
#include <cstring>
namespace rsspp {
void atom_parser::parse_feed(feed& f, xmlNode * rootNode) {
if (!rootNode)
throw exception(_("XML root node is NULL"));
f.language = get_prop(rootNode, "lang");
globalbase = get_prop(rootNode, "base", XML_URI);
for (xmlNode * node = rootNode->children; node != NULL; node = node->next) {
if (node_is(node, "title")) {
f.title = get_content(node);
f.title_type = get_prop(node, "type");
if (f.title_type == "")
f.title_type = "text";
} else if (node_is(node, "subtitle")) {
f.description = get_content(node);
} else if (node_is(node, "link")) {
std::string rel = get_prop(node, "rel");
if (rel == "alternate") {
f.link = newsbeuter::utils::absolute_url(globalbase, get_prop(node, "href"));
}
} else if (node_is(node, "updated")) {
f.pubDate = w3cdtf_to_rfc822(get_content(node));
} else if (node_is(node, "entry")) {
f.items.push_back(parse_entry(node));
}
}
}
item atom_parser::parse_entry(xmlNode * entryNode) {
item it;
std::string summary;
std::string summary_type;
std::string updated;
std::string base = get_prop(entryNode, "base", XML_URI);
if (base == "")
base = globalbase;
for (xmlNode * node = entryNode->children; node != NULL; node = node->next) {
if (node_is(node, "author")) {
for (xmlNode * authornode = node->children; authornode != NULL; authornode = authornode->next) {
if (node_is(authornode, "name")) {
it.author = get_content(authornode);
} // TODO: is there more?
}
} else if (node_is(node, "title")) {
it.title = get_content(node);
it.title_type = get_prop(node, "type");
if (it.title_type == "")
it.title_type = "text";
} else if (node_is(node, "content")) {
std::string mode = get_prop(node, "mode");
std::string type = get_prop(node, "type");
if (mode == "xml" || mode == "") {
if (type == "html" || type == "text") {
it.description = get_content(node);
} else {
it.description = get_xml_content(node);
}
} else if (mode == "escaped") {
it.description = get_content(node);
}
it.description_type = type;
if (it.description_type == "")
it.description_type = "text";
} else if (node_is(node, "id")) {
it.guid = get_content(node);
it.guid_isPermaLink = false;
} else if (node_is(node, "published")) {
it.pubDate = w3cdtf_to_rfc822(get_content(node));
} else if (node_is(node, "updated")) {
updated = w3cdtf_to_rfc822(get_content(node));
} else if (node_is(node, "link")) {
std::string rel = get_prop(node, "rel");
if (rel == "" || rel == "alternate") {
it.link = newsbeuter::utils::absolute_url(base, get_prop(node, "href"));
} else if (rel == "enclosure") {
it.enclosure_url = get_prop(node, "href");
it.enclosure_type = get_prop(node, "type");
}
} else if (node_is(node, "summary")) {
std::string mode = get_prop(node, "mode");
summary_type = get_prop(node, "type");
if (mode == "xml" || mode == "") {
if (summary_type == "html" || summary_type == "text") {
summary = get_content(node);
} else {
summary = get_xml_content(node);
}
} else if (mode == "escaped") {
summary = get_content(node);
}
if (summary_type == "")
summary_type = "text";
}
} // for
if (it.description == "") {
it.description = summary;
it.description_type = summary_type;
}
if (it.pubDate == "") {
it.pubDate = updated;
}
return it;
}
}
|
