summaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
authorRafi Ramadhana <42462215+rafiramadhana@users.noreply.github.com>2023-11-23 18:58:41 +0700
committerGitHub <noreply@github.com>2023-11-23 12:58:41 +0100
commitcbdbbd249239345f88bea031beb55e84c2f47688 (patch)
treef3b001d36c0da83a1827eb8008615f5f2577a638 /README.md
parent13322edf37510b6d3bb68a853368fd1a0a67a105 (diff)
Add custom request header (#18)
Diffstat (limited to 'README.md')
-rw-r--r--README.md28
1 files changed, 16 insertions, 12 deletions
diff --git a/README.md b/README.md
index 2f84843..cb7aacc 100644
--- a/README.md
+++ b/README.md
@@ -134,20 +134,24 @@ Below is an example scraping script that showcases the capabilities of flyscrape
```javascript
export const config = {
- url: "https://example.com/", // Specify the URL to start scraping from.
- urls: [ // Specify the URL(s) to start scraping from. If both `url` and `urls`
- "https://example.com/foo", // are provided, all of the specified URLs will be scraped.
+ url: "https://example.com/", // Specify the URL to start scraping from.
+ urls: [ // Specify the URL(s) to start scraping from. If both `url` and `urls`
+ "https://example.com/foo", // are provided, all of the specified URLs will be scraped.
"https://example.com/bar",
],
- depth: 0, // Specify how deep links should be followed. (default = 0, no follow)
- follow: [], // Speficy the css selectors to follow (default = ["a[href]"])
- allowedDomains: [], // Specify the allowed domains. ['*'] for all. (default = domain from url)
- blockedDomains: [], // Specify the blocked domains. (default = none)
- allowedURLs: [], // Specify the allowed URLs as regex. (default = all allowed)
- blockedURLs: [], // Specify the blocked URLs as regex. (default = none)
- rate: 100, // Specify the rate in requests per second. (default = no rate limit)
- proxies: [], // Specify the HTTP(S) proxy URLs. (default = no proxy)
- cache: "file", // Enable file-based request caching. (default = no cache)
+ depth: 0, // Specify how deep links should be followed. (default = 0, no follow)
+ follow: [], // Speficy the css selectors to follow (default = ["a[href]"])
+ allowedDomains: [], // Specify the allowed domains. ['*'] for all. (default = domain from url)
+ blockedDomains: [], // Specify the blocked domains. (default = none)
+ allowedURLs: [], // Specify the allowed URLs as regex. (default = all allowed)
+ blockedURLs: [], // Specify the blocked URLs as regex. (default = none)
+ rate: 100, // Specify the rate in requests per second. (default = no rate limit)
+ proxies: [], // Specify the HTTP(S) proxy URLs. (default = no proxy)
+ cache: "file", // Enable file-based request caching. (default = no cache)
+ headers: { // Specify the HTTP request header. (default = none)
+ "Authorization": "Basic ZGVtbzpwQDU1dzByZA==",
+ "User-Agent": "Gecko/1.0",
+ },
};
export function setup() {