diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 39972502..7eb2b1bb 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -45,7 +45,7 @@ jobs:
     - name: validate existing wacz
       run: docker-compose run crawler wacz validate --file collections/wr-net/wr-net.wacz
     - name: unzip wacz
-      run: docker-compose run crawler unzip collections/wr-net/wr-net.wacz -d collections/wr-net/wacz
+      run: sudo unzip crawls/collections/wr-net/wr-net.wacz -d crawls/collections/wr-net/wacz
     - name: run jest
       run: sudo yarn jest
         
diff --git a/Dockerfile b/Dockerfile
index f8d7a359..a28b8658 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,17 +1,31 @@
 ARG BROWSER_VERSION=90
 
-FROM oldwebtoday/chrome:${BROWSER_VERSION} as chrome
+ARG BROWSER_IMAGE_BASE=oldwebtoday/chrome
 
-FROM nikolaik/python-nodejs:python3.8-nodejs14
+ARG BROWSER_BIN=google-chrome
 
-RUN curl -sS https://dl.yarnpkg.com/debian/pubkey.gpg | apt-key add -
+FROM ${BROWSER_IMAGE_BASE}:${BROWSER_VERSION} as chrome
 
-RUN apt-get update -y \
-    && apt-get install --no-install-recommends -qqy fonts-stix locales-all redis-server xvfb \
+FROM ubuntu:bionic
+
+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 \
+	   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 -U setuptools
+
+# needed to add args to main build stage
 ARG BROWSER_VERSION
+ARG BROWSER_BIN
 
 ENV PROXY_HOST=localhost \
     PROXY_PORT=8080 \
@@ -19,7 +33,8 @@ ENV PROXY_HOST=localhost \
     PROXY_CA_FILE=/tmp/proxy-ca.pem \
     DISPLAY=:99 \
     GEOMETRY=1360x1020x16 \
-    BROWSER_VERSION=${BROWSER_VERSION}
+    BROWSER_VERSION=${BROWSER_VERSION} \
+    BROWSER_BIN=${BROWSER_BIN}
 
 COPY --from=chrome /tmp/*.deb /deb/
 COPY --from=chrome /app/libpepflashplayer.so /app/libpepflashplayer.so
diff --git a/README.md b/README.md
index 9de5f4f0..76d0d1f9 100644
--- a/README.md
+++ b/README.md
@@ -37,13 +37,14 @@ Here's how you can use some of the command-line options to configure the crawl:
 - To run more than one browser worker and crawl in parallel, and `--workers N` where N is number of browsers to run in parallel. More browsers will require more CPU and network bandwidth, and does not guarantee faster crawling.
 
 - To crawl into a new directory, specify a different name for the `--collection` param, or, if omitted, a new collection directory based on current time will be created.
--
 
 Browsertrix Crawler includes a number of additional command-line options, explained below.
 
 ## Crawling Configuration Options
 
-The Browsertrix Crawler docker image currently accepts the following parameters:
+
+<details>
+      <summary><b>The Browsertrix Crawler docker image currently accepts the following parameters:</b></summary>
 
 ```
 crawler [options]
@@ -136,6 +137,8 @@ Options:
                                            command line will take precedence.              
                                            [string]
 ```
+</details>
+
 
 For the `--waitUntil` flag,  see [page.goto waitUntil options](https://github.com/puppeteer/puppeteer/blob/main/docs/api.md#pagegotourl-options).
 
@@ -238,7 +241,7 @@ The current profile creation script is still experimental and the script attempt
 The Docker container provided here packages up several components used in Browsertrix.
 
 The system uses:
- - `oldwebtoday/chrome` - to install a recent version of Chrome (currently chrome:84)
+ - `oldwebtoday/chrome` or `oldwebtoday/chromium` - to install a recent version of Chrome (currently chrome:90) or Chromium (see below).
  - `puppeteer-cluster` - for running Chrome browsers in parallel
  - `pywb` - in recording mode for capturing the content
 
@@ -247,6 +250,19 @@ The crawl produces a single pywb collection, at `/crawls/collections/<collection
 
 To access the contents of the crawl, the `/crawls` directory in the container should be mounted to a volume (default in the Docker Compose setup).
 
+### Building with Custom Browser Image / Building on Apple M1
+
+Browsertrix Crawler can be built on the new ARM M1 chip (for development). However, since there is no Linux build of Chrome for ARM, Chromium can be used instead. Currently, Webrecorder provides the `oldwebtoday/chromium:91-arm` for running Browsertrix Crawler on ARM-based systems.
+
+For example, to build with this Chromium image on an Apple M1 machine, run:
+
+```
+docker-compose build --build-arg BROWSER_IMAGE_BASE=oldwebtoday/chromium --build-arg "BROWSER_VERSION=91-arm" --build-arg BROWSER_BIN=chromium-browser
+```
+
+You should then be able to run Browsertrix Crawler natively on M1. 
+
+The build arguments specify the base image, version and browser binary. This approach can also be used to install a different browser in general from any Debian-based Docker image.
 
 
 ### Example Usage
diff --git a/crawler.js b/crawler.js
index c8e297d8..d528654d 100644
--- a/crawler.js
+++ b/crawler.js
@@ -26,7 +26,7 @@ const  TextExtract  = require("./util/textextract");
 const { ScreenCaster } = require("./util/screencaster");
 const { parseArgs } = require("./util/argParser");
 
-const { CHROME_PATH, BEHAVIOR_LOG_FUNC, HTML_TYPES } = require("./util/constants");
+const { BROWSER_BIN, BEHAVIOR_LOG_FUNC, HTML_TYPES } = require("./util/constants");
 
 // ============================================================================
 class Crawler {
@@ -91,7 +91,7 @@ class Crawler {
       let version = process.env.BROWSER_VERSION;
 
       try {
-        version = child_process.execFileSync(CHROME_PATH, ["--product-version"], {encoding: "utf8"}).trim();
+        version = child_process.execFileSync(BROWSER_BIN, ["--product-version"], {encoding: "utf8"}).trim();
       } catch(e) {
         console.log(e);
       }
@@ -171,7 +171,7 @@ class Crawler {
     // Puppeter Options
     return {
       headless: this.params.headless,
-      executablePath: CHROME_PATH,
+      executablePath: BROWSER_BIN,
       ignoreHTTPSErrors: true,
       args: this.chromeArgs,
       userDataDir: this.profileDir,
@@ -255,9 +255,8 @@ class Crawler {
     const warcVersion = "WARC/1.1";
     const type = "warcinfo";
     const packageFileJSON = JSON.parse(await fsp.readFile("../app/package.json"));
-    const version = await fsp.readFile("/usr/local/lib/python3.8/site-packages/pywb/version.py", "utf8");
-    const pywbVersion = version.split("\n")[0].split("=")[1].trim().replace(/['"]+/g, "");
     const warcioPackageJson = JSON.parse(await fsp.readFile("/app/node_modules/warcio/package.json"));
+    const pywbVersion = child_process.execSync("pywb -V", {encoding: "utf8"}).trim().split(" ")[1];
 
     const info = {
       "software": `Browsertrix-Crawler ${packageFileJSON["version"]} (with warcio.js ${warcioPackageJson} pywb ${pywbVersion})`,
diff --git a/docker-compose.yml b/docker-compose.yml
index c330b964..28a28538 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -2,7 +2,7 @@ version: '3.5'
   
 services:
     crawler:
-        image: webrecorder/browsertrix-crawler:0.4.0-beta.1
+        image: webrecorder/browsertrix-crawler:0.4.0-beta.2
         build:
           context: ./
 
diff --git a/package.json b/package.json
index 89c3b3bf..6a15d20a 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "browsertrix-crawler",
-  "version": "0.4.0-beta.1",
+  "version": "0.4.0-beta.2",
   "main": "browsertrix-crawler",
   "repository": "https://github.com/webrecorder/browsertrix-crawler",
   "author": "Ilya Kreymer <ikreymer@gmail.com>, Webrecorder Software",
diff --git a/requirements.txt b/requirements.txt
index 52214951..087edfcb 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-pywb>=2.6.0b2
+pywb>=2.6.0b3
 #git+https://github.com/webrecorder/pywb@main
 uwsgi
 wacz>=0.3.0
diff --git a/util/constants.js b/util/constants.js
index c507c392..34f57c5a 100644
--- a/util/constants.js
+++ b/util/constants.js
@@ -2,5 +2,5 @@
 module.exports.HTML_TYPES = ["text/html", "application/xhtml", "application/xhtml+xml"];
 module.exports.WAIT_UNTIL_OPTS = ["load", "domcontentloaded", "networkidle0", "networkidle2"];
 module.exports.BEHAVIOR_LOG_FUNC = "__bx_log";
-module.exports.CHROME_PATH = "google-chrome";
+module.exports.BROWSER_BIN = process.env.BROWSER_BIN || "google-chrome";