Update to Chrome/Chromium 101 - (0.7.0 Beta 0) (#144)

* update base image 
- switch to browsertrix-base-image:101 with chrome/chromium 101,
- includes additional fonts and ubuntu 22.04 as base.
- add --disable-site-isolation-trials as default flag to support behaviors accessing iframes

* debugging support for shared redis state:
- support pausing crawler indefinitely if crawl state is set to 'debug'
- must be set/unset manually via external redis
- designed for browsertrix-cloud for now

bump to 0.7.0-beta.0

Dockerfile

@@ -1,35 +1,10 @@
-ARG BROWSER_VERSION=91
-
 ARG BROWSER_IMAGE_BASE=webrecorder/browsertrix-browser-base
+ARG BROWSER_VERSION=101
 
-ARG BROWSER_BIN=google-chrome
+FROM ${BROWSER_IMAGE_BASE}:${BROWSER_VERSION}
-
-FROM ${BROWSER_IMAGE_BASE}:${BROWSER_VERSION} AS browser
-
-FROM ubuntu:bionic
-
-# http://bugs.python.org/issue19846
-# > At the moment, setting "LANG=C" on a Linux system *fundamentally breaks Python 3*, and that's not OK.
-ENV LANG C.UTF-8
-
-RUN apt-get update -y && apt-get install --no-install-recommends -qqy software-properties-common \
-    && add-apt-repository -y ppa:deadsnakes \
-    && apt-get update -y \
-    && apt-get install --no-install-recommends -qqy build-essential fonts-stix locales-all redis-server xvfb gpg-agent curl git socat \
-	   python3.8 python3.8-distutils python3.8-dev gpg ca-certificates \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN curl -sS https://dl.yarnpkg.com/debian/pubkey.gpg | apt-key add - \
-    && echo "deb https://dl.yarnpkg.com/debian/ stable main" | tee /etc/apt/sources.list.d/yarn.list \
-    && curl -sL https://deb.nodesource.com/setup_16.x -o /tmp/nodesource_setup.sh && bash /tmp/nodesource_setup.sh \
-	&& apt-get update -y && apt-get install -qqy nodejs yarn \
-    && curl https://bootstrap.pypa.io/get-pip.py | python3.8 \
-    && pip install 'setuptools<58.0'
 
 # needed to add args to main build stage
 ARG BROWSER_VERSION
-ARG BROWSER_BIN
 
 ENV PROXY_HOST=localhost \
     PROXY_PORT=8080 \
@@ -38,16 +13,12 @@ ENV PROXY_HOST=localhost \
     DISPLAY=:99 \
     GEOMETRY=1360x1020x16 \
     BROWSER_VERSION=${BROWSER_VERSION} \
-    BROWSER_BIN=${BROWSER_BIN}
+    BROWSER_BIN=google-chrome
-
-COPY --from=browser /deb/*.deb /deb/
-RUN dpkg -i /deb/*.deb; apt-get update; apt-mark hold chromium-browser; apt --fix-broken install -qqy; \
-    rm -rf /var/lib/opts/lists/*
 
 WORKDIR /app
 
 ADD requirements.txt /app/
-RUN pip install -r requirements.txt
+RUN pip install -U setuptools; pip install -r requirements.txt
 
 ADD package.json /app/
 
@@ -62,8 +33,7 @@ ADD util/*.js /app/util/
 COPY config.yaml /app/
 ADD html/ /app/html/
 
-RUN ln -s /app/main.js /usr/bin/crawl
+RUN ln -s /app/main.js /usr/bin/crawl; ln -s /app/create-login-profile.js /usr/bin/create-login-profile
-RUN ln -s /app/create-login-profile.js /usr/bin/create-login-profile
 
 WORKDIR /crawls
 

crawler.js

@@ -168,7 +168,6 @@ class Crawler {
       this.statusLog(`Storing state via Redis ${redisUrl} @ key prefix "${this.crawlId}"`);
 
       this.crawlState = new RedisCrawlState(redis, this.params.crawlId, this.params.timeout * 2, os.hostname());
-      await this.crawlState.setStatus("running");
 
     } else {
       this.statusLog("Storing state in memory");
@@ -292,7 +291,9 @@ class Crawler {
     } finally {
       console.log(status);
 
+      if (this.crawlState) {
         await this.crawlState.setStatus(status);
+      }
 
       process.exit(this.exitCode);
     }
@@ -447,6 +448,18 @@ class Crawler {
       return;
     }
 
+    await this.initCrawlState();
+
+    let initState = await this.crawlState.getStatus();
+
+    while (initState === "debug") {
+      console.log("Paused for debugging, will continue after manual resume");
+
+      await this.sleep(60);
+
+      initState = await this.crawlState.getStatus();
+    }
+
     if (this.params.generateWACZ) {
       this.storage = initStorage();
     }
@@ -463,7 +476,9 @@ class Crawler {
     });
 
 
-    this.cluster.jobQueue = await this.initCrawlState();
+    this.cluster.jobQueue = this.crawlState;
+
+    await this.crawlState.setStatus("running");
 
     if (this.params.state) {
       await this.crawlState.load(this.params.state, this.params.scopedSeeds, true);

package.json

@@ -1,6 +1,6 @@
 {
   "name": "browsertrix-crawler",
-  "version": "0.6.0",
+  "version": "0.7.0-beta.0",
   "main": "browsertrix-crawler",
   "repository": "https://github.com/webrecorder/browsertrix-crawler",
   "author": "Ilya Kreymer <ikreymer@gmail.com>, Webrecorder Software",

util/browser.js

@@ -94,6 +94,7 @@ module.exports.chromeArgs = (proxy, userAgent=null, extraArgs=[]) => {
     "--enable-features=NetworkService,NetworkServiceInProcess",
     "--autoplay-policy=no-user-gesture-required",
     "--disable-features=IsolateOrigins,site-per-process,ImprovedCookieControls,LazyFrameLoading,GlobalMediaControls,DestroyProfileOnBrowserClose,MediaRouter,AcceptCHFrame,AutoExpandDetailsElement",
+    "--disable-site-isolation-trials",
     "--disable-popup-blocking",
     "--disable-backgrounding-occluded-windows",
     `--user-agent=${userAgent || getDefaultUA()}`,