Add the possibility to override default user agent for each feed
This commit is contained in:
parent
1d335390c2
commit
2538eea177
29 changed files with 129 additions and 22 deletions
|
@ -21,6 +21,7 @@ type FeedProcessor struct {
|
|||
scraperRules string
|
||||
rewriteRules string
|
||||
crawler bool
|
||||
userAgent string
|
||||
}
|
||||
|
||||
// WithCrawler enables the crawler.
|
||||
|
@ -33,6 +34,11 @@ func (f *FeedProcessor) WithScraperRules(rules string) {
|
|||
f.scraperRules = rules
|
||||
}
|
||||
|
||||
// WithUserAgent sets the User-Agent header for fetching article content.
|
||||
func (f *FeedProcessor) WithUserAgent(userAgent string) {
|
||||
f.userAgent = userAgent
|
||||
}
|
||||
|
||||
// WithRewriteRules adds rewrite rules to the processing.
|
||||
func (f *FeedProcessor) WithRewriteRules(rules string) {
|
||||
f.rewriteRules = rules
|
||||
|
@ -45,7 +51,7 @@ func (f *FeedProcessor) Process() {
|
|||
if f.store.EntryURLExists(f.userID, entry.URL) {
|
||||
logger.Debug(`[FeedProcessor] Do not crawl existing entry URL: "%s"`, entry.URL)
|
||||
} else {
|
||||
content, err := scraper.Fetch(entry.URL, f.scraperRules)
|
||||
content, err := scraper.Fetch(entry.URL, f.scraperRules, f.userAgent)
|
||||
if err != nil {
|
||||
logger.Error("[FeedProcessor] %v", err)
|
||||
} else {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue