reliq


Namereliq JSON
Version 0.0.26 PyPI version JSON
download
home_pageNone
SummaryPython ctypes bindings for reliq
upload_time2024-10-05 12:32:03
maintainerNone
docs_urlNone
authorNone
requires_python>=3.7
licenseGPLv3
keywords ctypes html parser text-processing
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # reliq-python

A python module for [reliq](https://github.com/TUVIMEN/reliq) library.

## Requirements

- [reliq](https://github.com/TUVIMEN/reliq)

## Installation

    pip install reliq

## Import

    from reliq import reliq

## Usage

```python
from reliq import reliq, ReliqError

html = ""
with open('index.html','r') as f:
    html = f.read()

rq = reliq(html) #parse html
expr = reliq.expr(r"""
    div .user; {
        a href; {
            .name * l@[0] | "%i"
            .link * l@[0] | "%(href)v"
        },
        .score.u span .score,
        .info dl; {
            .key dt | "%i",
            .value dd | "%i"
        },
        .achievements.a li class=b>"achievement-" | "%i\n"
    }
""") #expressions can be compiled

users = []
links = []
images = []

#filter()
#   returns object holding list of results such object
#   behaves like an array, but can be converted to array with
#       self() - objects with lvl() 0
#       children() - objects with lvl() 1
#       descendants() - objects with lvl > 0
#       full() - same as indexing filter(), all objects

for i in rq.filter(r'table; tr').self()[:-2]:
    #"i"
    #   It has a set of functions for getting its properties:
    #       tag()           tag name
    #       insides()       string containing contents inside tag
    #       desc_count()   count of descendants
    #       lvl()           level in html structure
    #       attribsl()      number of attributes
    #       attribs()       returns dictionary of attributes

    if i.child_count() < 3 and i[0].tag() == "div":
        continue

    #objects can be accessed as an array which is the same
    #as array returned by descendants() method
    link = i[5].attribs()['href']
    if re.match('^https://$',href):
        links.append(link)
        continue

    #search() returns str, in this case expression is already compiled
    user = json.loads(i.search(expr))
    users.append(user)

#reliq objects have __str__ method
#get_data() returns data from which the html structure has been compiled

#if the second argument of filter() is True the returned
#object will use independent data, allowing garbage collector
#to free the previous unused data

#fsearch()
#   executes expression at parsing saving memory, and because
#   of that it supports only chain expressions i.e use of
#   grouping brackets and separating commas will throw an exception
for i in reliq.fsearch(r'ul; img src | "%(src)v\n"',html).split('\n')[:-1]:
    images.append(i)

try: #handle errors
    reliq.fsearch('p / /','<p></p>')
except ReliqError:
    print("error")
```
## Projects using reliq

- [forumscraper](https://github.com/TUVIMEN/forumscraper)

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "reliq",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.7",
    "maintainer_email": null,
    "keywords": "ctypes, html, parser, text-processing",
    "author": null,
    "author_email": "Dominik Stanis\u0142aw Suchora <suchora.dominik7@gmail.com>",
    "download_url": "https://files.pythonhosted.org/packages/d8/cf/8757d7e1ebd0f9645c07e67850d5ac7301cfd62de8618a3c653b8b7f0000/reliq-0.0.26.tar.gz",
    "platform": null,
    "description": "# reliq-python\n\nA python module for [reliq](https://github.com/TUVIMEN/reliq) library.\n\n## Requirements\n\n- [reliq](https://github.com/TUVIMEN/reliq)\n\n## Installation\n\n    pip install reliq\n\n## Import\n\n    from reliq import reliq\n\n## Usage\n\n```python\nfrom reliq import reliq, ReliqError\n\nhtml = \"\"\nwith open('index.html','r') as f:\n    html = f.read()\n\nrq = reliq(html) #parse html\nexpr = reliq.expr(r\"\"\"\n    div .user; {\n        a href; {\n            .name * l@[0] | \"%i\"\n            .link * l@[0] | \"%(href)v\"\n        },\n        .score.u span .score,\n        .info dl; {\n            .key dt | \"%i\",\n            .value dd | \"%i\"\n        },\n        .achievements.a li class=b>\"achievement-\" | \"%i\\n\"\n    }\n\"\"\") #expressions can be compiled\n\nusers = []\nlinks = []\nimages = []\n\n#filter()\n#   returns object holding list of results such object\n#   behaves like an array, but can be converted to array with\n#       self() - objects with lvl() 0\n#       children() - objects with lvl() 1\n#       descendants() - objects with lvl > 0\n#       full() - same as indexing filter(), all objects\n\nfor i in rq.filter(r'table; tr').self()[:-2]:\n    #\"i\"\n    #   It has a set of functions for getting its properties:\n    #       tag()           tag name\n    #       insides()       string containing contents inside tag\n    #       desc_count()   count of descendants\n    #       lvl()           level in html structure\n    #       attribsl()      number of attributes\n    #       attribs()       returns dictionary of attributes\n\n    if i.child_count() < 3 and i[0].tag() == \"div\":\n        continue\n\n    #objects can be accessed as an array which is the same\n    #as array returned by descendants() method\n    link = i[5].attribs()['href']\n    if re.match('^https://$',href):\n        links.append(link)\n        continue\n\n    #search() returns str, in this case expression is already compiled\n    user = json.loads(i.search(expr))\n    users.append(user)\n\n#reliq objects have __str__ method\n#get_data() returns data from which the html structure has been compiled\n\n#if the second argument of filter() is True the returned\n#object will use independent data, allowing garbage collector\n#to free the previous unused data\n\n#fsearch()\n#   executes expression at parsing saving memory, and because\n#   of that it supports only chain expressions i.e use of\n#   grouping brackets and separating commas will throw an exception\nfor i in reliq.fsearch(r'ul; img src | \"%(src)v\\n\"',html).split('\\n')[:-1]:\n    images.append(i)\n\ntry: #handle errors\n    reliq.fsearch('p / /','<p></p>')\nexcept ReliqError:\n    print(\"error\")\n```\n## Projects using reliq\n\n- [forumscraper](https://github.com/TUVIMEN/forumscraper)\n",
    "bugtrack_url": null,
    "license": "GPLv3",
    "summary": "Python ctypes bindings for reliq",
    "version": "0.0.26",
    "project_urls": {
        "Homepage": "https://github.com/TUVIMEN/reliq-python"
    },
    "split_keywords": [
        "ctypes",
        " html",
        " parser",
        " text-processing"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "73448a42c16694306a7868c0b9e89bbb2fc6e29ffc193bd39d63a31abb695855",
                "md5": "82f2035e1d531aabc51155e66e91c575",
                "sha256": "3f78c4d4ac108ad9759e036bf3d8cbf7b403f04bc398688e9855286f12217309"
            },
            "downloads": -1,
            "filename": "reliq-0.0.26-cp310-cp310-manylinux2014_aarch64.whl",
            "has_sig": false,
            "md5_digest": "82f2035e1d531aabc51155e66e91c575",
            "packagetype": "bdist_wheel",
            "python_version": "cp310",
            "requires_python": ">=3.7",
            "size": 110833,
            "upload_time": "2024-10-05T12:31:52",
            "upload_time_iso_8601": "2024-10-05T12:31:52.917119Z",
            "url": "https://files.pythonhosted.org/packages/73/44/8a42c16694306a7868c0b9e89bbb2fc6e29ffc193bd39d63a31abb695855/reliq-0.0.26-cp310-cp310-manylinux2014_aarch64.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "c1683cb608dbdcc007b89b02401c5fc2d6555e80c71304c108fa07fc34b28c62",
                "md5": "49243927f50e4c7b9261fd58406fe1d6",
                "sha256": "ea7c794ab519f10214213ffd4223a7c9fc0622e70cf795a5b358f886b2eb822d"
            },
            "downloads": -1,
            "filename": "reliq-0.0.26-cp310-cp310-manylinux2014_armv7l.whl",
            "has_sig": false,
            "md5_digest": "49243927f50e4c7b9261fd58406fe1d6",
            "packagetype": "bdist_wheel",
            "python_version": "cp310",
            "requires_python": ">=3.7",
            "size": 90106,
            "upload_time": "2024-10-05T12:31:54",
            "upload_time_iso_8601": "2024-10-05T12:31:54.520107Z",
            "url": "https://files.pythonhosted.org/packages/c1/68/3cb608dbdcc007b89b02401c5fc2d6555e80c71304c108fa07fc34b28c62/reliq-0.0.26-cp310-cp310-manylinux2014_armv7l.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "86870ae76fe83d456aa8684e997300d12fbd20a22430ed26693ac8d8b1f755df",
                "md5": "f7b65c984b2a1a458e977207768962f2",
                "sha256": "f9643ab02b00e3fabee06a63ade3b55c0ba100ac5940164e887a297328f4629f"
            },
            "downloads": -1,
            "filename": "reliq-0.0.26-cp312-cp312-macosx_12_0_arm64.whl",
            "has_sig": false,
            "md5_digest": "f7b65c984b2a1a458e977207768962f2",
            "packagetype": "bdist_wheel",
            "python_version": "cp312",
            "requires_python": ">=3.7",
            "size": 90632,
            "upload_time": "2024-10-05T12:31:56",
            "upload_time_iso_8601": "2024-10-05T12:31:56.214652Z",
            "url": "https://files.pythonhosted.org/packages/86/87/0ae76fe83d456aa8684e997300d12fbd20a22430ed26693ac8d8b1f755df/reliq-0.0.26-cp312-cp312-macosx_12_0_arm64.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "922a22a564d9b238435a925f889560c90cfc4cab769824eee24d1d9786edb71e",
                "md5": "657f62cae15d85967a2c090d9e2a7d3a",
                "sha256": "a144a3ae78c467da213f4477bf885103bec646312555f3f0877cbdaee552990a"
            },
            "downloads": -1,
            "filename": "reliq-0.0.26-cp312-cp312-macosx_13_0_arm64.whl",
            "has_sig": false,
            "md5_digest": "657f62cae15d85967a2c090d9e2a7d3a",
            "packagetype": "bdist_wheel",
            "python_version": "cp312",
            "requires_python": ">=3.7",
            "size": 89594,
            "upload_time": "2024-10-05T12:31:57",
            "upload_time_iso_8601": "2024-10-05T12:31:57.858607Z",
            "url": "https://files.pythonhosted.org/packages/92/2a/22a564d9b238435a925f889560c90cfc4cab769824eee24d1d9786edb71e/reliq-0.0.26-cp312-cp312-macosx_13_0_arm64.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "8abafec348465298bd2258d1525ab590beb1835687e190e6ea29bc70553b34dc",
                "md5": "7010c8d347874d98a6cd03fef78fa15a",
                "sha256": "c9963fec09cdd91765846a13bc20993d68c07be5c91ddac9559c436ea2860d5c"
            },
            "downloads": -1,
            "filename": "reliq-0.0.26-cp312-cp312-manylinux2014_x86_64.whl",
            "has_sig": false,
            "md5_digest": "7010c8d347874d98a6cd03fef78fa15a",
            "packagetype": "bdist_wheel",
            "python_version": "cp312",
            "requires_python": ">=3.7",
            "size": 114241,
            "upload_time": "2024-10-05T12:31:59",
            "upload_time_iso_8601": "2024-10-05T12:31:59.921093Z",
            "url": "https://files.pythonhosted.org/packages/8a/ba/fec348465298bd2258d1525ab590beb1835687e190e6ea29bc70553b34dc/reliq-0.0.26-cp312-cp312-manylinux2014_x86_64.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "94543b60f0da317467cafa12dee15029d248907608f8137eff5e1422c5359242",
                "md5": "9e0dc2fa839ffbf8a291d49bea8812cc",
                "sha256": "66c5e38d7023b2773ce043565c94161a456d9af3c9ad41349b9a10784ad95d27"
            },
            "downloads": -1,
            "filename": "reliq-0.0.26-cp312-cp312-win_amd64.whl",
            "has_sig": false,
            "md5_digest": "9e0dc2fa839ffbf8a291d49bea8812cc",
            "packagetype": "bdist_wheel",
            "python_version": "cp312",
            "requires_python": ">=3.7",
            "size": 143602,
            "upload_time": "2024-10-05T12:32:01",
            "upload_time_iso_8601": "2024-10-05T12:32:01.593344Z",
            "url": "https://files.pythonhosted.org/packages/94/54/3b60f0da317467cafa12dee15029d248907608f8137eff5e1422c5359242/reliq-0.0.26-cp312-cp312-win_amd64.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "d8cf8757d7e1ebd0f9645c07e67850d5ac7301cfd62de8618a3c653b8b7f0000",
                "md5": "9538b8df2437b0c00481f0e79ff326a1",
                "sha256": "df445473a1ef1ba832b9df8b2bd357a7cffd52db3859b4141856bba71d47eab4"
            },
            "downloads": -1,
            "filename": "reliq-0.0.26.tar.gz",
            "has_sig": false,
            "md5_digest": "9538b8df2437b0c00481f0e79ff326a1",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.7",
            "size": 17619,
            "upload_time": "2024-10-05T12:32:03",
            "upload_time_iso_8601": "2024-10-05T12:32:03.225448Z",
            "url": "https://files.pythonhosted.org/packages/d8/cf/8757d7e1ebd0f9645c07e67850d5ac7301cfd62de8618a3c653b8b7f0000/reliq-0.0.26.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-10-05 12:32:03",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "TUVIMEN",
    "github_project": "reliq-python",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "lcname": "reliq"
}
        
Elapsed time: 0.36843s