Merge pull request #201 from openzim/lang

crawler 0.10.2

.github/workflows/ci.yaml

@@ -17,4 +17,4 @@ jobs:
         run: docker run -v $PWD/output:/output zimit zimit --url http://isago.rskg.org/ --name isago --zim-file isago.zim --adminEmail test@example.com --mobileDevice "Pixel 5" --statsFilename /output/stats.json --keep
 
       - name: run integration test suite
-        run: docker run -v $PWD/test/integration.py:/app/integration.py -v $PWD/output:/output zimit bash -c "pip install pytest; pytest -v ./integration.py"
+        run: docker run -v $PWD/test/integration.py:/app/integration.py -v $PWD/output:/output zimit bash -c "/app/zimit/bin/pip install pytest; /app/zimit/bin/pytest -v ./integration.py"

CHANGELOG.md

@@ -12,14 +12,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `--title` to set ZIM title
 - `--description` to set ZIM description
 - New crawler options: `--maxPageLimit`, `--delay`, `--diskUtilization`
+- `--zim-lang` param to set warc2zim's `--lang` (ISO-639-3)
 
 ### Changed
 
-- Using browsertrix-crawler 0.10.0-beta.4
+- Using browsertrix-crawler 0.10.2
 - Default and accepted values for `--waitUntil` from crawler's update
 - Using `main` warc2zim ⚠️ change before releasing!
 - Disabled Chrome updates to prevent incidental inclusion of update data in WARC/ZIM (#172)
 - `--failOnFailedSeed` used inconditionally
+- `--lang` now passed to crawler (ISO-639-1)
 
 ### Removed
 

Dockerfile

@@ -1,33 +1,35 @@
- FROM webrecorder/browsertrix-crawler:0.10.0-beta.4
+FROM webrecorder/browsertrix-crawler:0.10.2
 LABEL org.opencontainers.image.source https://github.com/openzim/zimit
 
-RUN apt-get update && apt-get install -qqy --no-install-recommends libmagic1 && apt-get clean && rm -rf /var/lib/apt/lists/*
-
-# temp (needs warc2zim release on zimit release)
-RUN pip3 install --no-cache-dir 'requests>=2.24.0' 'inotify==0.2.10' 'tld>=0.12,<0.13' 'warc2zim==1.5.1' && \
-    pip3 uninstall -y warc2zim && \
-    pip3 install 'git+https://github.com/openzim/warc2zim@main#egg_name=warc2zim'
-
-RUN mkdir -p /output
-
-WORKDIR /app
-
-# download list of bad domains to filter-out. intentionnaly ran post-install
-# so it's not cached in earlier layers (url stays same but content updated)
-RUN mkdir -p /tmp/ads && cd /tmp/ads && \
+RUN apt-get update \
+    && apt-get install -qqy --no-install-recommends \
+        libmagic1 \
+        python3.10-venv \
+    && rm -rf /var/lib/apt/lists/* \
+    # python setup (in venv not to conflict with browsertrix)
+    && python3 -m venv /app/zimit \
+    && /app/zimit/bin/python -m pip install --no-cache-dir 'requests==2.31.0' 'inotify==0.2.10' 'tld==0.13' 'warc2zim==1.5.2' \
+    # placeholder (default output location)
+    && mkdir -p /output \
+    # disable chrome upgrade
+    && printf "repo_add_once=\"false\"\nrepo_reenable_on_distupgrade=\"false\"\n" > /etc/default/google-chrome \
+    # download list of bad domains to filter-out. intentionnaly ran post-install \
+    # so it's not cached in earlier layers (url stays same but content updated) \
+    mkdir -p /tmp/ads && cd /tmp/ads && \
     curl -L -O https://hosts.anudeep.me/mirror/adservers.txt && \
     curl -L -O https://hosts.anudeep.me/mirror/CoinMiner.txt && \
     curl -L -O https://hosts.anudeep.me/mirror/facebook.txt && \
     cat ./*.txt > /etc/blocklist.txt \
-    && rm ./*.txt
-RUN printf '#!/bin/sh\ncat /etc/blocklist.txt >> /etc/hosts\nexec "$@"' > /usr/local/bin/entrypoint.sh && \
+    && rm ./*.txt \
+    && printf '#!/bin/sh\ncat /etc/blocklist.txt >> /etc/hosts\nexec "$@"' > /usr/local/bin/entrypoint.sh && \
     chmod +x /usr/local/bin/entrypoint.sh
 
+WORKDIR /app
 ADD zimit.py /app/
-
-RUN ln -s /app/zimit.py /usr/bin/zimit
-
-RUN printf "repo_add_once=\"false\"\nrepo_reenable_on_distupgrade=\"false\"\n" > /etc/default/google-chrome
+# fix shebang on zimit to use in-venv python
+RUN sed -i.bak "1 s/.*/#!\/app\/zimit\/bin\/python3/" /app/zimit.py \
+    && ln -s /app/zimit.py /usr/bin/zimit \
+    && chmod +x /usr/bin/zimit
 
 ENTRYPOINT ["entrypoint.sh"]
 CMD ["zimit"]

zimit.py

@@ -205,6 +205,18 @@ def zimit(args=None):
         action="store_true",
     )
 
+    parser.add_argument(
+        "--lang",
+        help="if set, sets the language used by the browser, should be ISO 639 language[-country] code",
+    )
+
+    parser.add_argument(
+        "--zim-lang",
+        help="Language metadata of ZIM "
+        "(warc2zim --lang param). ISO-639-3 code. "
+        "Retrieved from homepage if found, fallback to `eng`",
+    )
+
     parser.add_argument(
         "--mobileDevice",
         help="Emulate mobile device by name from "
@@ -348,6 +360,10 @@ def zimit(args=None):
         warc2zim_args.append("--description")
         warc2zim_args.append(zimit_args.description)
 
+    if zimit_args.zim_lang:
+        warc2zim_args.append("--lang")
+        warc2zim_args.append(zimit_args.zim_lang)
+
     print("----------")
     print("Testing warc2zim args")
     print("Running: warc2zim " + " ".join(warc2zim_args), flush=True)
@@ -482,6 +498,7 @@ def get_node_cmd_line(args):
         "exclude",
         "collection",
         "allowHashUrls",
+        "lang",
         "mobileDevice",
         "userAgent",
         "useSitemap",