mirror of
https://github.com/pacnpal/Roo-Code.git
synced 2025-12-22 13:21:07 -05:00
Refactor
This commit is contained in:
@@ -12,7 +12,7 @@ interface PCRStats {
|
||||
executablePath: string
|
||||
}
|
||||
|
||||
export class UrlScraper {
|
||||
export class UrlContentFetcher {
|
||||
private context: vscode.ExtensionContext
|
||||
private browser?: Browser
|
||||
private page?: Page
|
||||
@@ -74,8 +74,7 @@ export class UrlScraper {
|
||||
/*
|
||||
- networkidle2 is equivalent to playwright's networkidle where it waits until there are no more than 2 network connections for at least 500 ms.
|
||||
- domcontentloaded is when the basic DOM is loaded
|
||||
this should be sufficient for most doc sites, but we can use the more elaborate waitTillHTMLRendered if we find users are scraping more dynamic complex sites
|
||||
https://stackoverflow.com/questions/52497252/puppeteer-wait-until-page-is-completely-loaded/61304202#61304202
|
||||
this should be sufficient for most doc sites
|
||||
*/
|
||||
await this.page.goto(url, { timeout: 10_000, waitUntil: ["domcontentloaded", "networkidle2"] })
|
||||
const content = await this.page.content()
|
||||
@@ -1,7 +1,7 @@
|
||||
import * as vscode from "vscode"
|
||||
import * as path from "path"
|
||||
import { openFile } from "./open-file"
|
||||
import { UrlScraper } from "./UrlScraper"
|
||||
import { UrlContentFetcher } from "./UrlContentFetcher"
|
||||
import { mentionRegexGlobal } from "../shared/context-mentions"
|
||||
import fs from "fs/promises"
|
||||
import { extractTextFromFile } from "./extract-text"
|
||||
@@ -32,7 +32,7 @@ export function openMention(mention?: string): void {
|
||||
}
|
||||
}
|
||||
|
||||
export async function parseMentions(text: string, cwd: string, urlScraper: UrlScraper): Promise<string> {
|
||||
export async function parseMentions(text: string, cwd: string, urlContentFetcher: UrlContentFetcher): Promise<string> {
|
||||
const mentions: Set<string> = new Set()
|
||||
let parsedText = text.replace(mentionRegexGlobal, (match, mention) => {
|
||||
mentions.add(mention)
|
||||
@@ -53,7 +53,7 @@ export async function parseMentions(text: string, cwd: string, urlScraper: UrlSc
|
||||
let launchBrowserError: Error | undefined
|
||||
if (urlMention) {
|
||||
try {
|
||||
await urlScraper.launchBrowser()
|
||||
await urlContentFetcher.launchBrowser()
|
||||
} catch (error) {
|
||||
launchBrowserError = error
|
||||
vscode.window.showErrorMessage(`Error fetching content for ${urlMention}: ${error.message}`)
|
||||
@@ -67,7 +67,7 @@ export async function parseMentions(text: string, cwd: string, urlScraper: UrlSc
|
||||
result = `Error fetching content: ${launchBrowserError.message}`
|
||||
} else {
|
||||
try {
|
||||
const markdown = await urlScraper.urlToMarkdown(mention)
|
||||
const markdown = await urlContentFetcher.urlToMarkdown(mention)
|
||||
result = markdown
|
||||
} catch (error) {
|
||||
vscode.window.showErrorMessage(`Error fetching content for ${mention}: ${error.message}`)
|
||||
@@ -103,7 +103,7 @@ export async function parseMentions(text: string, cwd: string, urlScraper: UrlSc
|
||||
|
||||
if (urlMention) {
|
||||
try {
|
||||
await urlScraper.closeBrowser()
|
||||
await urlContentFetcher.closeBrowser()
|
||||
} catch (error) {
|
||||
console.error(`Error closing browser: ${error.message}`)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user