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
|
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package processor // import "miniflux.app/v2/internal/reader/processor"
import (
"log/slog"
"net/url"
"slices"
"time"
"miniflux.app/v2/internal/config"
"miniflux.app/v2/internal/metric"
"miniflux.app/v2/internal/model"
"miniflux.app/v2/internal/proxyrotator"
"miniflux.app/v2/internal/reader/fetcher"
"miniflux.app/v2/internal/reader/filter"
"miniflux.app/v2/internal/reader/readingtime"
"miniflux.app/v2/internal/reader/rewrite"
"miniflux.app/v2/internal/reader/sanitizer"
"miniflux.app/v2/internal/reader/scraper"
"miniflux.app/v2/internal/reader/urlcleaner"
"miniflux.app/v2/internal/storage"
)
// ProcessFeedEntries downloads original web page for entries and apply filters.
func ProcessFeedEntries(store *storage.Storage, feed *model.Feed, userID int64, forceRefresh bool) {
var filteredEntries model.Entries
user, storeErr := store.UserByID(userID)
if storeErr != nil {
slog.Error("Database error", slog.Any("error", storeErr))
return
}
// The errors are handled in RemoveTrackingParameters.
parsedFeedURL, _ := url.Parse(feed.FeedURL)
parsedSiteURL, _ := url.Parse(feed.SiteURL)
blockRules := filter.ParseRules(user.BlockFilterEntryRules, feed.BlockFilterEntryRules)
allowRules := filter.ParseRules(user.KeepFilterEntryRules, feed.KeepFilterEntryRules)
slog.Debug("Filter rules",
slog.String("user_block_filter_rules", user.BlockFilterEntryRules),
slog.String("feed_block_filter_rules", feed.BlockFilterEntryRules),
slog.String("user_keep_filter_rules", user.KeepFilterEntryRules),
slog.String("feed_keep_filter_rules", feed.KeepFilterEntryRules),
slog.Any("block_rules", blockRules),
slog.Any("allow_rules", allowRules),
slog.Int64("user_id", user.ID),
slog.Int64("feed_id", feed.ID),
)
requestBuilder := fetcher.NewRequestBuilder()
requestBuilder.WithUserAgent(feed.UserAgent, config.Opts.HTTPClientUserAgent())
requestBuilder.WithCookie(feed.Cookie)
requestBuilder.WithTimeout(config.Opts.HTTPClientTimeout())
requestBuilder.WithProxyRotator(proxyrotator.ProxyRotatorInstance)
requestBuilder.WithCustomFeedProxyURL(feed.ProxyURL)
requestBuilder.WithCustomApplicationProxyURL(config.Opts.HTTPClientProxyURL())
requestBuilder.UseCustomApplicationProxyURL(feed.FetchViaProxy)
requestBuilder.IgnoreTLSErrors(feed.AllowSelfSignedCertificates)
requestBuilder.DisableHTTP2(feed.DisableHTTP2)
// Processing older entries first ensures that their creation timestamp is lower than newer entries.
for _, entry := range slices.Backward(feed.Entries) {
slog.Debug("Processing entry",
slog.Int64("user_id", user.ID),
slog.String("entry_url", entry.URL),
slog.String("entry_hash", entry.Hash),
slog.String("entry_title", entry.Title),
slog.Int64("feed_id", feed.ID),
slog.String("feed_url", feed.FeedURL),
)
if filter.IsBlockedEntry(blockRules, allowRules, feed, entry) {
slog.Debug("Entry is blocked by filter rules",
slog.Int64("user_id", user.ID),
slog.String("entry_url", entry.URL),
slog.String("entry_hash", entry.Hash),
slog.String("entry_title", entry.Title),
slog.Int64("feed_id", feed.ID),
slog.String("feed_url", feed.FeedURL),
)
continue
}
parsedInputUrl, _ := url.Parse(entry.URL)
if cleanedURL, err := urlcleaner.RemoveTrackingParameters(parsedFeedURL, parsedSiteURL, parsedInputUrl); err == nil {
entry.URL = cleanedURL
}
webpageBaseURL := ""
entry.URL = rewrite.RewriteEntryURL(feed, entry)
entryIsNew := store.IsNewEntry(feed.ID, entry.Hash)
if feed.Crawler && (entryIsNew || forceRefresh) {
slog.Debug("Scraping entry",
slog.Int64("user_id", user.ID),
slog.String("entry_url", entry.URL),
slog.String("entry_hash", entry.Hash),
slog.String("entry_title", entry.Title),
slog.Int64("feed_id", feed.ID),
slog.String("feed_url", feed.FeedURL),
slog.Bool("entry_is_new", entryIsNew),
slog.Bool("force_refresh", forceRefresh),
)
startTime := time.Now()
scrapedPageBaseURL, extractedContent, scraperErr := scraper.ScrapeWebsite(
requestBuilder,
entry.URL,
feed.ScraperRules,
)
if scrapedPageBaseURL != "" {
webpageBaseURL = scrapedPageBaseURL
}
if config.Opts.HasMetricsCollector() {
status := "success"
if scraperErr != nil {
status = "error"
}
metric.ScraperRequestDuration.WithLabelValues(status).Observe(time.Since(startTime).Seconds())
}
if scraperErr != nil {
slog.Warn("Unable to scrape entry",
slog.Int64("user_id", user.ID),
slog.String("entry_url", entry.URL),
slog.Int64("feed_id", feed.ID),
slog.String("feed_url", feed.FeedURL),
slog.Any("error", scraperErr),
)
} else if extractedContent != "" {
// We replace the entry content only if the scraper doesn't return any error.
entry.Content = minifyContent(extractedContent)
}
}
rewrite.ApplyContentRewriteRules(entry, feed.RewriteRules)
if webpageBaseURL == "" {
webpageBaseURL = entry.URL
}
// The sanitizer should always run at the end of the process to make sure unsafe HTML is filtered out.
entry.Content = sanitizer.SanitizeHTML(webpageBaseURL, entry.Content, &sanitizer.SanitizerOptions{OpenLinksInNewTab: user.OpenExternalLinksInNewTab})
updateEntryReadingTime(store, feed, entry, entryIsNew, user)
filteredEntries = append(filteredEntries, entry)
}
if user.ShowReadingTime && shouldFetchYouTubeWatchTimeInBulk() {
fetchYouTubeWatchTimeInBulk(filteredEntries)
}
feed.Entries = filteredEntries
}
// ProcessEntryWebPage downloads the entry web page and apply rewrite rules.
func ProcessEntryWebPage(feed *model.Feed, entry *model.Entry, user *model.User) error {
startTime := time.Now()
entry.URL = rewrite.RewriteEntryURL(feed, entry)
requestBuilder := fetcher.NewRequestBuilder()
requestBuilder.WithUserAgent(feed.UserAgent, config.Opts.HTTPClientUserAgent())
requestBuilder.WithCookie(feed.Cookie)
requestBuilder.WithTimeout(config.Opts.HTTPClientTimeout())
requestBuilder.WithProxyRotator(proxyrotator.ProxyRotatorInstance)
requestBuilder.WithCustomFeedProxyURL(feed.ProxyURL)
requestBuilder.WithCustomApplicationProxyURL(config.Opts.HTTPClientProxyURL())
requestBuilder.UseCustomApplicationProxyURL(feed.FetchViaProxy)
requestBuilder.IgnoreTLSErrors(feed.AllowSelfSignedCertificates)
requestBuilder.DisableHTTP2(feed.DisableHTTP2)
webpageBaseURL, extractedContent, scraperErr := scraper.ScrapeWebsite(
requestBuilder,
entry.URL,
feed.ScraperRules,
)
if config.Opts.HasMetricsCollector() {
status := "success"
if scraperErr != nil {
status = "error"
}
metric.ScraperRequestDuration.WithLabelValues(status).Observe(time.Since(startTime).Seconds())
}
if scraperErr != nil {
return scraperErr
}
if extractedContent != "" {
entry.Content = minifyContent(extractedContent)
if user.ShowReadingTime {
entry.ReadingTime = readingtime.EstimateReadingTime(entry.Content, user.DefaultReadingSpeed, user.CJKReadingSpeed)
}
}
rewrite.ApplyContentRewriteRules(entry, entry.Feed.RewriteRules)
entry.Content = sanitizer.SanitizeHTML(webpageBaseURL, entry.Content, &sanitizer.SanitizerOptions{OpenLinksInNewTab: user.OpenExternalLinksInNewTab})
return nil
}
|
