diff --git a/.ansible/roles/common_server/tasks/docker.yaml b/.ansible/roles/common_server/tasks/docker.yaml new file mode 100644 index 0000000..08a74db --- /dev/null +++ b/.ansible/roles/common_server/tasks/docker.yaml @@ -0,0 +1,22 @@ +- name: "Docker" + tags: + - docker + block: + - name: "Docker: packages" + tags: + - install + package: + name: "{{ item }}" + state: latest + loop: + - "docker.io" + - "docker-compose" + become: yes + + - name: "Docker: directory" + tags: + - install + file: + state: directory + path: "/srv/app/docker" + become: yes diff --git a/.ansible/roles/haproxy_server/files/haproxy.cfg b/.ansible/roles/haproxy_server/files/haproxy.cfg index 8ced83d..1cb2de6 100644 --- a/.ansible/roles/haproxy_server/files/haproxy.cfg +++ b/.ansible/roles/haproxy_server/files/haproxy.cfg @@ -87,7 +87,7 @@ backend matrix-backend server localhost 10.0.9.111:8008 maxconn 64 backend searx-backend - server localhost 127.0.0.1:8888 + server localhost 10.0.9.111:8888 acl network_allowed src 10.0.9.0/24 backend share-backend diff --git a/.ansible/roles/linux_desktop/vars/main.yaml b/.ansible/roles/linux_desktop/vars/main.yaml index 02fd6a1..6f176b6 100644 --- a/.ansible/roles/linux_desktop/vars/main.yaml +++ b/.ansible/roles/linux_desktop/vars/main.yaml @@ -60,6 +60,7 @@ gnome_extension_ids: - 1206 # clock-override - 28 # gtile - 1386 # notification counter + - 1034 # systemd unit toggles gnome_custom_keybindings: - name: 'Show CopyQ clipboards' diff --git a/.ansible/roles/matrix_server/files/log.yaml b/.ansible/roles/matrix_server/files/log.yaml deleted file mode 100644 index 9d7acb8..0000000 --- a/.ansible/roles/matrix_server/files/log.yaml +++ /dev/null @@ -1,37 +0,0 @@ -version: 1 - -formatters: - precise: - format: "%(asctime)s - %(name)s - %(lineno)d - %(levelname)s - %(request)s - %(message)s" - -filters: - context: - (): synapse.logging.context.LoggingContextFilter - request: "" - -handlers: - file: - class: logging.handlers.RotatingFileHandler - formatter: precise - filename: /var/log/matrix-synapse/homeserver.log - maxBytes: 104857600 - backupCount: 10 - filters: [context] - encoding: utf8 - console: - class: logging.StreamHandler - formatter: precise - level: WARN - -loggers: - synapse: - level: WARN - - synapse.storage.SQL: - # beware: increasing this to DEBUG will make synapse log sensitive - # information such as access tokens. - level: WARN - -root: - level: WARN - handlers: [file, console] diff --git a/.ansible/roles/matrix_server/tasks/includes/repos.yaml b/.ansible/roles/matrix_server/tasks/includes/repos.yaml deleted file mode 100644 index 55e7d02..0000000 --- a/.ansible/roles/matrix_server/tasks/includes/repos.yaml +++ /dev/null @@ -1,19 +0,0 @@ -- name: includes/repos.yaml - tags: - - install - - repos - - matrix - block: - - name: "Apt repo: Import GPG key: {{ repo.name }}" - apt_key: - state: present - url: "{{ repo.key }}" - when: repo.key - become: true - - - name: "Apt repo: Add repo: {{ repo.name }}" - apt_repository: - state: present - repo: "{{ repo.data }}" - update_cache: yes - become: true diff --git a/.ansible/roles/matrix_server/tasks/main.yaml b/.ansible/roles/matrix_server/tasks/main.yaml index 5e3d9ae..332e2f3 100644 --- a/.ansible/roles/matrix_server/tasks/main.yaml +++ b/.ansible/roles/matrix_server/tasks/main.yaml @@ -1,60 +1,14 @@ -- name: "Matrix: Repositories" - tags: - - install - - repos - - matrix - include: includes/repos.yaml - loop: "{{ linux_repos }}" - loop_control: - loop_var: repo - -- name: "Matrix: Packages" - tags: - - install - - packages - - matrix - package: - name: "{{ item }}" - state: present - loop: "{{ linux_packages }}" - become: true - - name: "Matrix: Configuration" tags: - config - matrix block: + - include: roles/common_server/tasks/docker.yaml + - name: "Matrix: Configuration: homeserver.yaml" template: src: "templates/homeserver.yaml.j2" - dest: "/etc/matrix-synapse/homeserver.yaml" - mode: "0400" - owner: "matrix-synapse" - group: "nogroup" - become: yes - - - name: "Matrix: Configuration: server_name.yaml" - copy: - dest: "/etc/matrix-synapse/conf.d/server_name.yaml" - content: "server_name: home.suborbit.com" - mode: "0400" - owner: "matrix-synapse" - group: "nogroup" - become: yes - - - name: "Matrix: Configuration: log.yaml" - copy: - dest: "/etc/matrix-synapse/log.yaml" - src: "files/log.yaml" - mode: "0400" - owner: "matrix-synapse" - group: "nogroup" - become: yes - - - name: "Matrix: Configuration: dhparam.pem" - copy: - dest: "/etc/matrix-synapse/dhparam.pem" - content: "{{ dhparam }}" + dest: "/srv/app/docker/matrix/config/homeserver.yaml" mode: "0400" owner: "matrix-synapse" group: "nogroup" @@ -62,18 +16,16 @@ - name: "Matrix: Configuration: homeserver.signing.key" copy: - dest: "/etc/matrix-synapse/homeserver.signing.key" + dest: "/srv/app/docker/matrix/config/homeserver.signing.key" content: "{{ signing_key }}" mode: "0400" owner: "matrix-synapse" group: "nogroup" become: yes -- name: "Matrix: Service" - tags: - - matrix - systemd: - name: "matrix-synapse" - state: started - enabled: yes - become: yes + - name: "Matrix: Docker: compose.yaml" + copy: + dest: "/srv/app/docker/matrix/compose.yaml" + src: "files/docker-compose.yaml" + mode: "0400" + become: yes diff --git a/.ansible/roles/matrix_server/templates/homeserver.yaml.j2 b/.ansible/roles/matrix_server/templates/homeserver.yaml.j2 index a3cbd36..092a3d6 100644 --- a/.ansible/roles/matrix_server/templates/homeserver.yaml.j2 +++ b/.ansible/roles/matrix_server/templates/homeserver.yaml.j2 @@ -3,6 +3,7 @@ tls_fingerprints: [{ "sha256": "/HCvvvL0fZZb3BsgA8KIegBijVjk4UCbA9od18BLxOE" }] pid_file: /run/matrix-synapse.pid soft_file_limit: 0 use_presence: true +server_name: home.suborbit.com listeners: - port: 8008 tls: false @@ -17,9 +18,8 @@ listeners: database: name: "sqlite3" args: - database: "/var/lib/matrix-synapse/homeserver.db" + database: "/data/homeserver.db" event_cache_size: "10K" -log_config: "/etc/matrix-synapse/log.yaml" rc_messages_per_second: 0.2 rc_message_burst_count: 10.0 federation_rc_window_size: 1000 @@ -27,8 +27,8 @@ federation_rc_sleep_limit: 10 federation_rc_sleep_delay: 500 federation_rc_reject_limit: 5 federation_rc_concurrent: 1 -media_store_path: "/var/lib/matrix-synapse/media" -uploads_path: "/var/lib/matrix-synapse/uploads" +media_store_path: "/data/media" +uploads_path: "/data/uploads" max_upload_size: "100M" max_image_pixels: "64M" dynamic_thumbnails: false @@ -76,7 +76,7 @@ room_invite_state_types: app_service_config_files: [] track_appservice_user_ips: False expire_access_token: False -signing_key_path: "/etc/matrix-synapse/homeserver.signing.key" +signing_key_path: "/config/homeserver.signing.key" old_signing_keys: {} key_refresh_interval: "1d" # 1 Day. trusted_key_servers: diff --git a/.ansible/roles/matrix_server/vars/main.yaml b/.ansible/roles/matrix_server/vars/main.yaml index f93a0da..a8fc01e 100644 --- a/.ansible/roles/matrix_server/vars/main.yaml +++ b/.ansible/roles/matrix_server/vars/main.yaml @@ -1,12 +1,4 @@ --- -linux_repos: - - name: "Matrix Synapse" - data: "deb https://packages.matrix.org/debian disco main" - key: "https://packages.matrix.org/debian/matrix-org-archive-keyring.gpg" - -linux_packages: - - matrix-synapse-py3 - password_pepper: !vault | $ANSIBLE_VAULT;1.1;AES256 33373335643631373939643231653138646134633537343138333461633164393764376236663065 diff --git a/.ansible/roles/media_server/files/cloudplow.service b/.ansible/roles/media_server/files/cloudplow.service deleted file mode 100644 index bf98758..0000000 --- a/.ansible/roles/media_server/files/cloudplow.service +++ /dev/null @@ -1,17 +0,0 @@ -[Unit] -Description=cloudplow -After=mnt-media.mount -Requires=mnt-media.mount - -[Service] -User=media -Group=media -Type=simple -WorkingDirectory=/srv/app/cloudplow/ -ExecStart=/srv/app/cloudplow/.venv/bin/python3 /srv/app/cloudplow/cloudplow.py run --loglevel=INFO -ExecStopPost=/bin/rm -rf /srv/app/cloudplow/locks -Restart=always -RestartSec=10 - -[Install] -WantedBy=default.target diff --git a/.ansible/roles/media_server/files/cloudplow_config.json b/.ansible/roles/media_server/files/cloudplow_config.json deleted file mode 100644 index 214a75b..0000000 --- a/.ansible/roles/media_server/files/cloudplow_config.json +++ /dev/null @@ -1,61 +0,0 @@ -{ - "core": { - "dry_run": false, - "rclone_binary_path": "/usr/bin/rclone", - "rclone_config_path": "/srv/etc/rclone/rclone.conf" - }, - "hidden": { - "/mnt/.media.cache/.unionfs": { - "hidden_remotes": [ - "google" - ] - } - }, - "notifications": {}, - "remotes": { - "google": { - "hidden_remote": "GoogleDriveCrypt:", - "rclone_command": "move", - "rclone_excludes": [ - "**partial~", - "**_HIDDEN~", - ".unionfs/**" - ], - "rclone_extras": { - "--bwlimit": "23:00,off 07:00,1M", - "--checkers": 16, - "--drive-chunk-size": "64M", - "--skip-links": null, - "--stats": "60s", - "--transfers": 4, - "--verbose": 1 - }, - "rclone_sleeps": { - "Failed to copy: googleapi: Error 403: User rate limit exceeded": { - "count": 5, - "sleep": 25, - "timeout": 3600 - } - }, - "remove_empty_dir_depth": 2, - "sync_remote": "GoogleDriveCrypt:", - "upload_folder": "/mnt/.media.cache", - "upload_remote": "GoogleDriveCloudplowUpload:" - } - }, - "syncer": {}, - "uploader": { - "google": { - "check_interval": 1, - "exclude_open_files": true, - "max_size_gb": 10, - "opened_excludes": [], - "schedule": { - "allowed_from": "04:00", - "allowed_until": "08:00", - "enabled": false - }, - "size_excludes": [] - } - } -} diff --git a/.ansible/roles/media_server/files/docker-compose.yaml b/.ansible/roles/media_server/files/docker-compose.yaml index 04f8cf0..9f64b71 100644 --- a/.ansible/roles/media_server/files/docker-compose.yaml +++ b/.ansible/roles/media_server/files/docker-compose.yaml @@ -62,7 +62,7 @@ services: volumes: - /srv/app/docker/mediaserver/config/radarr:/config - /mnt/media/_Movies:/movies - - /srv/tmp/downloads/complete/movies:/downloads + - /srv/tmp/downloads:/downloads ports: - 7878:7878 restart: unless-stopped @@ -77,7 +77,7 @@ services: - UMASK_SET=022 volumes: - /srv/app/docker/mediaserver/config/sabnzbd:/config - - /srv/tmp/downloads/complete:/downloads + - /srv/tmp/downloads:/downloads - /srv/tmp/downloads/incomplete:/incomplete-downloads ports: - 8080:8080 @@ -95,7 +95,22 @@ services: volumes: - /srv/app/docker/mediaserver/config/sonarr:/config - /mnt/media/_TV:/tv - - /srv/tmp/downloads/complete/tv:/downloads + - /srv/tmp/downloads:/downloads ports: - 8989:8989 restart: unless-stopped + + cloudplow: + image: sabrsorensen/alpine-cloudplow + container_name: cloudplow + environment: + - PUID=1003 + - PGID=1003 + - TZ=Europe/London + - UMASK_SET=022 + volumes: + - /srv/app/docker/mediaserver/config/cloudplow:/config:rw + - /srv/etc/rclone:/config/rclone:rw + - /mnt/.media.cache:/data/imported_media:rw + - /etc/localtime:/etc/localtime:ro + restart: unless-stopped diff --git a/.ansible/roles/media_server/tasks/main.yaml b/.ansible/roles/media_server/tasks/main.yaml index 2316277..166d760 100644 --- a/.ansible/roles/media_server/tasks/main.yaml +++ b/.ansible/roles/media_server/tasks/main.yaml @@ -2,10 +2,11 @@ tags: - mediaserver block: + - include: roles/common_server/tasks/docker.yaml + - name: "Media Server: Group" tags: - install - - cloudplow group: name: "media" become: yes @@ -13,7 +14,6 @@ - name: "Media Server: User" tags: - install - - cloudplow user: name: "media" group: "media" @@ -21,100 +21,24 @@ expires: -1 become: yes - - name: "Media Server: Cloudplow: git repo" + - name: "Media Server: directories" tags: - - install - - cloudplow - git: - repo: "https://github.com/l3uddz/cloudplow.git" - dest: "/srv/app/cloudplow" - become: yes - - - name: "Media Server: Cloudplow: directory permissions" - tags: - - install - - cloudplow + - config file: - path: "/srv/app/cloudplow" + path: "{{ item }}" state: directory - mode: "u+w" owner: "media" group: "media" - recurse: yes - become: yes - - - name: "Media Server: Cloudplow: config" - tags: - - config - - cloudplow - copy: - src: "files/cloudplow_config.json" - dest: "/srv/app/cloudplow/config.json" - mode: "0600" - owner: "media" - group: "media" - become: yes - - - name: "Media Server: Cloudplow: Python dependencies" - tags: - - install - - cloudplow - pip: - requirements: "/srv/app/cloudplow/requirements.txt" - virtualenv: "/srv/app/cloudplow/.venv" - virtualenv_python: python3 - become: yes - - - name: "Media Server: Cloudplow: service config" - tags: - - install - - cloudplow - copy: - dest: "/etc/systemd/system/cloudplow.service" - src: "files/cloudplow.service" - mode: "0644" - become: yes - - - name: "Media Server: Cloudplow: service" - tags: - - config - - cloudplow - systemd: - name: "cloudplow" - state: started - enabled: yes - daemon_reload: yes - become: yes - - - name: "Media Server: Docker: packages" - tags: - - install - - docker - package: - name: "{{ item }}" - state: latest loop: - - "docker.io" - - "docker-compose" + - "/srv/app/docker/mediaserver" + - "/srv/app/docker/mediaserver/config" become: yes - - name: "Media Server: Docker: directories" + - name: "Media Server: Docker: compose.yaml" tags: - config - - docker - file: - path: "/srv/app/docker/mediaserver/config" - state: directory - owner: "media" - group: "media" - recurse: yes - become: yes - - - name: "Media Server: Docker: config" - tags: - - config - - docker copy: dest: "/srv/app/docker/mediaserver/compose.yaml" src: "files/docker-compose.yaml" + mode: "0400" become: yes diff --git a/.ansible/roles/rclone_mount/files/rclone.service b/.ansible/roles/rclone_mount/files/rclone.service index b96b461..06be899 100644 --- a/.ansible/roles/rclone_mount/files/rclone.service +++ b/.ansible/roles/rclone_mount/files/rclone.service @@ -13,10 +13,8 @@ ExecStart=/usr/bin/rclone mount \ --allow-other \ --no-modtime \ --read-only \ - --dir-cache-time=240m \ --tpslimit=10 \ --tpslimit-burst=1 \ - --buffer-size=1G \ GoogleDriveCrypt:/ /mnt/GoogleDriveCrypt ExecStartPost=/bin/bash -c 'while [ ! -d /mnt/GoogleDriveCrypt/_Other ]; do /usr/bin/sleep 5; done' ExecStop=/bin/fusermount -u /mnt/GoogleDriveCrypt diff --git a/.ansible/roles/searx_server/files/docker-compose.yaml b/.ansible/roles/searx_server/files/docker-compose.yaml new file mode 100644 index 0000000..fd4c0b6 --- /dev/null +++ b/.ansible/roles/searx_server/files/docker-compose.yaml @@ -0,0 +1,21 @@ +--- +version: "2" +services: + searx: + image: hoellen/searx + container_name: searx + environment: + - UID=1002 + - GID=1002 + - TZ=Europe/London + - UMASK_SET=022 + volumes: + - /srv/app/docker/searx/config/settings.yml:/usr/local/searx/searx/settings.yml:ro + - /srv/app/docker/searx/config/plugins/open_results_on_new_tab.py:/usr/local/searx/searx/plugins/open_results_on_new_tab.py:ro + - /srv/app/docker/searx/config/plugins/oa_doi_rewrite.py:/usr/local/searx/searx/plugins/oa_doi_rewrite.py:ro + - /srv/app/docker/searx/config/plugins/infinite_scroll.py:/usr/local/searx/searx/plugins/infinite_scroll.py:ro + - /srv/app/docker/searx/config/engines/google.py:/usr/local/searx/searx/engines/google.py:ro + + ports: + - 8888:8888 + restart: unless-stopped diff --git a/.ansible/roles/searx_server/files/engines/google.py b/.ansible/roles/searx_server/files/engines/google.py new file mode 100644 index 0000000..6381d61 --- /dev/null +++ b/.ansible/roles/searx_server/files/engines/google.py @@ -0,0 +1,443 @@ +# Google (Web) +# +# @website https://www.google.com +# @provide-api yes (https://developers.google.com/custom-search/) +# +# @using-api no +# @results HTML +# @stable no (HTML can change) +# @parse url, title, content, suggestion + +import re +from flask_babel import gettext +from lxml import html, etree +from searx.engines.xpath import extract_text, extract_url +from searx import logger +from searx.url_utils import urlencode, urlparse, parse_qsl +from searx.utils import match_language + +logger = logger.getChild('google engine') + + +# engine dependent config +categories = ['general'] +paging = True +language_support = True +use_locale_domain = True +time_range_support = True + +# based on https://en.wikipedia.org/wiki/List_of_Google_domains and tests +default_hostname = 'www.google.com' + +country_to_hostname = { + 'BG': 'www.google.bg', # Bulgaria + 'CZ': 'www.google.cz', # Czech Republic + 'DE': 'www.google.de', # Germany + 'DK': 'www.google.dk', # Denmark + 'AT': 'www.google.at', # Austria + 'CH': 'www.google.ch', # Switzerland + 'GR': 'www.google.gr', # Greece + 'AU': 'www.google.com.au', # Australia + 'CA': 'www.google.ca', # Canada + 'GB': 'www.google.co.uk', # United Kingdom + 'ID': 'www.google.co.id', # Indonesia + 'IE': 'www.google.ie', # Ireland + 'IN': 'www.google.co.in', # India + 'MY': 'www.google.com.my', # Malaysia + 'NZ': 'www.google.co.nz', # New Zealand + 'PH': 'www.google.com.ph', # Philippines + 'SG': 'www.google.com.sg', # Singapore + # 'US': 'www.google.us', # United States, redirect to .com + 'ZA': 'www.google.co.za', # South Africa + 'AR': 'www.google.com.ar', # Argentina + 'CL': 'www.google.cl', # Chile + 'ES': 'www.google.es', # Spain + 'MX': 'www.google.com.mx', # Mexico + 'EE': 'www.google.ee', # Estonia + 'FI': 'www.google.fi', # Finland + 'BE': 'www.google.be', # Belgium + 'FR': 'www.google.fr', # France + 'IL': 'www.google.co.il', # Israel + 'HR': 'www.google.hr', # Croatia + 'HU': 'www.google.hu', # Hungary + 'IT': 'www.google.it', # Italy + 'JP': 'www.google.co.jp', # Japan + 'KR': 'www.google.co.kr', # South Korea + 'LT': 'www.google.lt', # Lithuania + 'LV': 'www.google.lv', # Latvia + 'NO': 'www.google.no', # Norway + 'NL': 'www.google.nl', # Netherlands + 'PL': 'www.google.pl', # Poland + 'BR': 'www.google.com.br', # Brazil + 'PT': 'www.google.pt', # Portugal + 'RO': 'www.google.ro', # Romania + 'RU': 'www.google.ru', # Russia + 'SK': 'www.google.sk', # Slovakia + 'SI': 'www.google.si', # Slovenia + 'SE': 'www.google.se', # Sweden + 'TH': 'www.google.co.th', # Thailand + 'TR': 'www.google.com.tr', # Turkey + 'UA': 'www.google.com.ua', # Ukraine + # 'CN': 'www.google.cn', # China, only from China ? + 'HK': 'www.google.com.hk', # Hong Kong + 'TW': 'www.google.com.tw' # Taiwan +} + +# osm +url_map = 'https://www.openstreetmap.org/'\ + + '?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M' + +# search-url +search_path = '/search' +search_url = ('https://{hostname}' + + search_path + + '?{query}&start={offset}&gws_rd=cr&gbv=1&lr={lang}&hl={lang_short}&ei=x') + +time_range_search = "&tbs=qdr:{range}" +time_range_dict = {'day': 'd', + 'week': 'w', + 'month': 'm', + 'year': 'y'} + +# other URLs +map_hostname_start = 'maps.google.' +maps_path = '/maps' +redirect_path = '/url' +images_path = '/images' +supported_languages_url = 'https://www.google.com/preferences?#languages' + +# specific xpath variables +results_xpath = '//div[@class="g"]' +url_xpath = './/h3/a/@href' +title_xpath = './/h3' +content_xpath = './/span[@class="st"]' +content_misc_xpath = './/div[@class="f slp"]' +suggestion_xpath = '//p[@class="_Bmc"]' +spelling_suggestion_xpath = '//a[@class="spell"]' + +# map : detail location +map_address_xpath = './/div[@class="s"]//table//td[2]/span/text()' +map_phone_xpath = './/div[@class="s"]//table//td[2]/span/span' +map_website_url_xpath = 'h3[2]/a/@href' +map_website_title_xpath = 'h3[2]' + +# map : near the location +map_near = 'table[@class="ts"]//tr' +map_near_title = './/h4' +map_near_url = './/h4/a/@href' +map_near_phone = './/span[@class="nobr"]' + +# images +images_xpath = './/div/a' +image_url_xpath = './@href' +image_img_src_xpath = './img/@src' + +# property names +# FIXME : no translation +property_address = "Address" +property_phone = "Phone number" + + +# remove google-specific tracking-url +def parse_url(url_string, google_hostname): + # sanity check + if url_string is None: + return url_string + + # normal case + parsed_url = urlparse(url_string) + if (parsed_url.netloc in [google_hostname, ''] + and parsed_url.path == redirect_path): + query = dict(parse_qsl(parsed_url.query)) + return query['q'] + else: + return url_string + + +# returns extract_text on the first result selected by the xpath or None +def extract_text_from_dom(result, xpath): + r = result.xpath(xpath) + if len(r) > 0: + return extract_text(r[0]) + return None + + +# do search-request +def request(query, params): + offset = (params['pageno'] - 1) * 10 + + if params['language'] == 'all' or params['language'] == 'en-US': + language = 'en-GB' + else: + language = match_language(params['language'], supported_languages, {}) + + language_array = language.split('-') + if params['language'].find('-') > 0: + country = params['language'].split('-')[1] + elif len(language_array) == 2: + country = language_array[1] + else: + country = 'US' + + url_lang = 'lang_' + language + + if use_locale_domain: + google_hostname = country_to_hostname.get(country.upper(), default_hostname) + else: + google_hostname = default_hostname + + # original format: ID=3e2b6616cee08557:TM=5556667580:C=r:IP=4.1.12.5-:S=23ASdf0soFgF2d34dfgf-_22JJOmHdfgg + params['cookies']['GOOGLE_ABUSE_EXEMPTION'] = 'x' + params['url'] = search_url.format(offset=offset, + query=urlencode({'q': query}), + hostname=google_hostname, + lang=url_lang, + lang_short=language) + if params['time_range'] in time_range_dict: + params['url'] += time_range_search.format(range=time_range_dict[params['time_range']]) + + params['headers']['Accept-Language'] = language + ',' + language + '-' + country + params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' + + # Force Internet Explorer 12 user agent to avoid loading the new UI that Searx can't parse + params['headers']['User-Agent'] = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)" + + params['google_hostname'] = google_hostname + + return params + + +# get response from search-request +def response(resp): + results = [] + + # detect google sorry + resp_url = urlparse(resp.url) + if resp_url.netloc == 'sorry.google.com' or resp_url.path == '/sorry/IndexRedirect': + raise RuntimeWarning('sorry.google.com') + + if resp_url.path.startswith('/sorry'): + raise RuntimeWarning(gettext('CAPTCHA required')) + + # which hostname ? + google_hostname = resp.search_params.get('google_hostname') + google_url = "https://" + google_hostname + + # convert the text to dom + dom = html.fromstring(resp.text) + + instant_answer = dom.xpath('//div[@id="_vBb"]//text()') + if instant_answer: + results.append({'answer': u' '.join(instant_answer)}) + try: + results_num = int(dom.xpath('//div[@id="resultStats"]//text()')[0] + .split()[1].replace(',', '')) + results.append({'number_of_results': results_num}) + except: + pass + + # parse results + for result in dom.xpath(results_xpath): + try: + title = extract_text(result.xpath(title_xpath)[0]) + url = parse_url(extract_url(result.xpath(url_xpath), google_url), google_hostname) + parsed_url = urlparse(url, google_hostname) + + # map result + if parsed_url.netloc == google_hostname: + # TODO fix inside links + continue + # if parsed_url.path.startswith(maps_path) or parsed_url.netloc.startswith(map_hostname_start): + # print "yooooo"*30 + # x = result.xpath(map_near) + # if len(x) > 0: + # # map : near the location + # results = results + parse_map_near(parsed_url, x, google_hostname) + # else: + # # map : detail about a location + # results = results + parse_map_detail(parsed_url, result, google_hostname) + # # google news + # elif parsed_url.path == search_path: + # # skipping news results + # pass + + # # images result + # elif parsed_url.path == images_path: + # # only thumbnail image provided, + # # so skipping image results + # # results = results + parse_images(result, google_hostname) + # pass + + else: + # normal result + content = extract_text_from_dom(result, content_xpath) + if content is None: + continue + content_misc = extract_text_from_dom(result, content_misc_xpath) + if content_misc is not None: + content = content_misc + "
" + content + # append result + results.append({'url': url, + 'title': title, + 'content': content + }) + except: + logger.debug('result parse error in:\n%s', etree.tostring(result, pretty_print=True)) + continue + + logger.debug(results) + if not results: + logger.debug('SCOTT trying new interface') + a_tags = dom.xpath('//a') + for a_tag in a_tags: + href = a_tag.get('href', '') + url = dict(parse_qsl(href)).get('/url?q', None) + if not (url and url.startswith('http')): + continue + ancestors = [x for x in a_tag.iterancestors()] + try: + title_divs = a_tag.xpath('./div') + if title_divs: + title = title_divs[0].text.strip().replace('\n', ' ').replace(' ', ' ') + else: + title = None + item_div = ancestors[2] + content_divs = item_div.xpath('./div/div[3]/div/div/div/div/div[1]/div') + if content_divs: + content = content_divs[0].text.strip() + else: + content_divs = item_div.xpath('./div/div[3]/div/div/div/div/div') + if content_divs: + content = content_divs[0].text.strip().replace('\n', ' ').replace(' ', ' ') + else: + content = None + if not content: + content_divs = ancestors[1].xpath('./div/div/div/div/div/div') + if content_divs: + content = extract_text(content_divs[0]) + pass + if title or content: + if any(x['url'] == url for x in results): + results_item = results.pop( + results.index( + [x for x in results if x['url'] == url][0])) + for key, var in (('title', title), ('content', content)): + if not results_item[key]: + results_item[key] = var + results.append(results_item) + else: + results.append({ + 'url': url, 'title': title, 'content': content}) + except Exception as err: + logger.error(err, exc_info=1) + + # parse suggestion + for suggestion in dom.xpath(suggestion_xpath): + # append suggestion + results.append({'suggestion': extract_text(suggestion)}) + + for correction in dom.xpath(spelling_suggestion_xpath): + results.append({'correction': extract_text(correction)}) + + # return results + return results + + +def parse_images(result, google_hostname): + results = [] + for image in result.xpath(images_xpath): + url = parse_url(extract_text(image.xpath(image_url_xpath)[0]), google_hostname) + img_src = extract_text(image.xpath(image_img_src_xpath)[0]) + + # append result + results.append({'url': url, + 'title': '', + 'content': '', + 'img_src': img_src, + 'template': 'images.html' + }) + + return results + + +def parse_map_near(parsed_url, x, google_hostname): + results = [] + + for result in x: + title = extract_text_from_dom(result, map_near_title) + url = parse_url(extract_text_from_dom(result, map_near_url), google_hostname) + attributes = [] + phone = extract_text_from_dom(result, map_near_phone) + add_attributes(attributes, property_phone, phone, 'tel:' + phone) + results.append({'title': title, + 'url': url, + 'content': attributes_to_html(attributes) + }) + + return results + + +def parse_map_detail(parsed_url, result, google_hostname): + results = [] + + # try to parse the geoloc + m = re.search(r'@([0-9\.]+),([0-9\.]+),([0-9]+)', parsed_url.path) + if m is None: + m = re.search(r'll\=([0-9\.]+),([0-9\.]+)\&z\=([0-9]+)', parsed_url.query) + + if m is not None: + # geoloc found (ignored) + lon = float(m.group(2)) # noqa + lat = float(m.group(1)) # noqa + zoom = int(m.group(3)) # noqa + + # attributes + attributes = [] + address = extract_text_from_dom(result, map_address_xpath) + phone = extract_text_from_dom(result, map_phone_xpath) + add_attributes(attributes, property_address, address, 'geo:' + str(lat) + ',' + str(lon)) + add_attributes(attributes, property_phone, phone, 'tel:' + phone) + + # title / content / url + website_title = extract_text_from_dom(result, map_website_title_xpath) + content = extract_text_from_dom(result, content_xpath) + website_url = parse_url(extract_text_from_dom(result, map_website_url_xpath), google_hostname) + + # add a result if there is a website + if website_url is not None: + results.append({'title': website_title, + 'content': (content + '
' if content is not None else '') + + attributes_to_html(attributes), + 'url': website_url + }) + + return results + + +def add_attributes(attributes, name, value, url): + if value is not None and len(value) > 0: + attributes.append({'label': name, 'value': value, 'url': url}) + + +def attributes_to_html(attributes): + retval = '' + for a in attributes: + value = a.get('value') + if 'url' in a: + value = '' + value + '' + retval = retval + '' + retval = retval + '
' + a.get('label') + '' + value + '
' + return retval + + +# get supported languages from their site +def _fetch_supported_languages(resp): + supported_languages = {} + dom = html.fromstring(resp.text) + options = dom.xpath('//*[@id="langSec"]//input[@name="lr"]') + for option in options: + code = option.xpath('./@value')[0].split('_')[-1] + name = option.xpath('./@data-name')[0].title() + supported_languages[code] = {"name": name} + + return supported_languages diff --git a/.ansible/roles/searx_server/files/plugins/infinite_scroll.py b/.ansible/roles/searx_server/files/plugins/infinite_scroll.py new file mode 100644 index 0000000..40c1f3e --- /dev/null +++ b/.ansible/roles/searx_server/files/plugins/infinite_scroll.py @@ -0,0 +1,9 @@ +from flask_babel import gettext + +name = gettext('Infinite scroll') +description = gettext('Automatically load next page when scrolling to bottom of current page') +default_on = True +preference_section = 'ui' + +js_dependencies = ('plugins/js/infinite_scroll.js',) +css_dependencies = ('plugins/css/infinite_scroll.css',) diff --git a/.ansible/roles/searx_server/files/plugins/oa_doi_rewrite.py b/.ansible/roles/searx_server/files/plugins/oa_doi_rewrite.py new file mode 100644 index 0000000..db0b73b --- /dev/null +++ b/.ansible/roles/searx_server/files/plugins/oa_doi_rewrite.py @@ -0,0 +1,45 @@ +from flask_babel import gettext +import re +from searx.url_utils import urlparse, parse_qsl +from searx import settings + + +regex = re.compile(r'10\.\d{4,9}/[^\s]+') + +name = gettext('Open Access DOI rewrite') +description = gettext('Avoid paywalls by redirecting to open-access versions of publications when available') +default_on = True +preference_section = 'general' + +doi_resolvers = settings['doi_resolvers'] + + +def extract_doi(url): + match = regex.search(url.path) + if match: + return match.group(0) + for _, v in parse_qsl(url.query): + match = regex.search(v) + if match: + return match.group(0) + return None + + +def get_doi_resolver(args, preference_doi_resolver): + doi_resolvers = settings['doi_resolvers'] + doi_resolver = args.get('doi_resolver', preference_doi_resolver)[0] + if doi_resolver not in doi_resolvers: + doi_resolvers = settings['default_doi_resolver'] + doi_resolver_url = doi_resolvers[doi_resolver] + return doi_resolver_url + + +def on_result(request, search, result): + doi = extract_doi(result['parsed_url']) + if doi and len(doi) < 50: + for suffix in ('/', '.pdf', '/full', '/meta', '/abstract'): + if doi.endswith(suffix): + doi = doi[:-len(suffix)] + result['url'] = get_doi_resolver(request.args, request.preferences.get_value('doi_resolver')) + doi + result['parsed_url'] = urlparse(result['url']) + return True diff --git a/.ansible/roles/searx_server/files/plugins/open_results_on_new_tab.py b/.ansible/roles/searx_server/files/plugins/open_results_on_new_tab.py new file mode 100644 index 0000000..e67568d --- /dev/null +++ b/.ansible/roles/searx_server/files/plugins/open_results_on_new_tab.py @@ -0,0 +1,25 @@ +''' +searx is free software: you can redistribute it and/or modify +it under the terms of the GNU Affero General Public License as published by +the Free Software Foundation, either version 3 of the License, or +(at your option) any later version. + +searx is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU Affero General Public License for more details. + +You should have received a copy of the GNU Affero General Public License +along with searx. If not, see < http://www.gnu.org/licenses/ >. + +(C) 2016 by Adam Tauber, +''' +from flask_babel import gettext +name = gettext('Open result links on new browser tabs') +description = gettext('Results are opened in the same window by default. ' + 'This plugin overwrites the default behaviour to open links on new tabs/windows. ' + '(JavaScript required)') +default_on = True +preference_section = 'ui' + +js_dependencies = ('plugins/js/open_results_on_new_tab.js',) diff --git a/.ansible/roles/searx_server/files/uwsgi.ini b/.ansible/roles/searx_server/files/uwsgi.ini deleted file mode 100644 index 4391322..0000000 --- a/.ansible/roles/searx_server/files/uwsgi.ini +++ /dev/null @@ -1,28 +0,0 @@ -[uwsgi] -# Who will run the code -uid = www-data -gid = www-data - -# disable logging for privacy -#disable-logging = true - -# Number of workers (usually CPU count) -workers = 4 - -# The right granted on the created socket -chmod-socket = 666 -http-socket = [::]:8888 - -# Plugin to use and interpretor config -single-interpreter = true -master = true -plugin = python -enable-threads = true -lazy-apps = true - -# Module to import -module = searx.webapp - -virtualenv = /srv/app/searx/searx-ve/ -pythonpath = /srv/app/searx/ -chdir = /srv/app/searx/searx/ diff --git a/.ansible/roles/searx_server/tasks/main.yaml b/.ansible/roles/searx_server/tasks/main.yaml index c90666c..511cc13 100644 --- a/.ansible/roles/searx_server/tasks/main.yaml +++ b/.ansible/roles/searx_server/tasks/main.yaml @@ -1,45 +1,47 @@ -- name: 'Searx' +- name: "Searx" tags: - - install - searx block: - - name: 'Searx: package' - package: - name: "{{ item }}" - state: latest - become: yes - loop: - - uwsgi - - uwsgi-plugin-python3 + - include: roles/common_server/tasks/docker.yaml - - name: 'Searx: Config directory' + - name: "Searx: Config directory" + tags: + - install file: state: directory - path: '/srv/app/searx/searx' + path: "{{ item }}" + loop: + - "/srv/app/docker/searx" + - "/srv/app/docker/searx/config" + - "/srv/app/docker/searx/config/plugins" + - "/srv/app/docker/searx/config/engines" become: yes - - name: 'Searx: Config' + - name: "Searx: Config: main" + tags: + - config + template: + dest: "/srv/app/docker/searx/config/settings.yml" + src: "templates/settings.yaml.j2" + mode: "0400" + become: yes + + - name: "Searx: Config: overrides" + tags: + - config copy: - dest: '/srv/app/searx/searx/settings.yml' - src: 'files/settings.yaml' + dest: "/srv/app/docker/searx/config/{{ item }}/" + src: "files/{{ item }}/" + loop: + - "plugins" + - "engines" become: yes - - name: 'Searx: UWSGI integration' + - name: "Searx: Docker: compose.yaml" + tags: + - config copy: - dest: '/etc/uwsgi/apps-available/searx.ini' - src: 'files/uwsgi.ini' - become: yes - - - name: 'Searx: UWSGI enable' - file: - dest: '/etc/uwsgi/apps-enabled/searx.ini' - src: '/etc/uwsgi/apps-available/searx.ini' - state: link - become: yes - - - name: 'Searx: UWSGI service' - systemd: - name: 'uwsgi' - state: started - enabled: yes + dest: "/srv/app/docker/searx/compose.yaml" + src: "files/docker-compose.yaml" + mode: "0400" become: yes diff --git a/.ansible/roles/searx_server/files/settings.yaml b/.ansible/roles/searx_server/templates/settings.yaml.j2 similarity index 97% rename from .ansible/roles/searx_server/files/settings.yaml rename to .ansible/roles/searx_server/templates/settings.yaml.j2 index 07a33ce..477ac6f 100644 --- a/.ansible/roles/searx_server/files/settings.yaml +++ b/.ansible/roles/searx_server/templates/settings.yaml.j2 @@ -5,21 +5,21 @@ general: search: safe_search : 1 # Filter results. 0: None, 1: Moderate, 2: Strict autocomplete : "google" # Existing autocomplete backends: "dbpedia", "duckduckgo", "google", "startpage", "wikipedia" - leave blank to turn it off by default - language : "en-GB" + language : "en-US" ban_time_on_fail : 5 # ban time in seconds after engine errors max_ban_time_on_fail : 120 # max ban time in seconds after engine errors server: - port : 8889 - bind_address : "::" # address to listen on - secret_key : "notused" + port : 8888 + bind_address : "0.0.0.0" # address to listen on + secret_key : "{{ secret }}" base_url : False # Set custom base_url. Possible values: False or "https://your.custom.host/location/" image_proxy : False # Proxying image results through searx http_protocol_version : "1.0" # 1.0 and 1.1 are supported ui: - static_path : "/srv/app/searx/searx/static" # Custom static path - leave it blank if you didn't change - templates_path : "/srv/app/searx/searx/templates" # Custom templates path - leave it blank if you didn't change + static_path : "/usr/local/searx/searx/static" # Custom static path - leave it blank if you didn't change + templates_path : "/usr/local/searx/searx/templates" # Custom templates path - leave it blank if you didn't change default_theme : oscar # ui theme default_locale : "" # Default interface locale - leave blank to detect from browser information or use codes from the 'locales' config section theme_args : @@ -52,12 +52,6 @@ outgoing: # communication with search engines # - 1.1.1.2 engines: - - name: apk mirror - engine: apkmirror - timeout: 4.0 - shortcut: apkm - disabled: True - - name : arch linux wiki engine : archlinux shortcut : al @@ -394,12 +388,6 @@ engines: timeout : 6.0 disabled : True - - name : invidious - engine : invidious - base_url : 'https://invidio.us/' - shortcut: iv - timeout : 5.0 - - name: kickass engine : kickass shortcut : kc @@ -605,7 +593,7 @@ engines: engine : startpage shortcut : sp timeout : 6.0 - disabled : False + disabled : True - name : tokyotoshokan engine : tokyotoshokan @@ -639,11 +627,6 @@ engines: # content_xpath : //*[@class="meaning"] # shortcut : ud - - name : unsplash - engine : unsplash - disabled: True - shortcut : us - - name : yahoo engine : yahoo shortcut : yh diff --git a/.ansible/roles/searx_server/vars/main.yaml b/.ansible/roles/searx_server/vars/main.yaml new file mode 100644 index 0000000..2da8c23 --- /dev/null +++ b/.ansible/roles/searx_server/vars/main.yaml @@ -0,0 +1,8 @@ +secret: !vault | + $ANSIBLE_VAULT;1.1;AES256 + 62623164336563316535333233306263613666643734616665396236353432343562313230663161 + 3833623732373932633366303533366633346133313935300a306131383764306637373738333039 + 36376462303161623430613734303234353731303664313138356432333732396661303832636263 + 3263646364323234620a316539313161303539376337653565656239636666353434306533656535 + 33346334386134643830653762663130316363653136303933306661313933613964326663366531 + 3036366164393838353034336339343234643764636438353834