{"id":45575468,"url":"https://github.com/hansalemaos/lxml2pandas","last_synced_at":"2026-02-23T09:01:07.659Z","repository":{"id":202701226,"uuid":"707968407","full_name":"hansalemaos/lxml2pandas","owner":"hansalemaos","description":"lxml to pandas for fast web scraping","archived":false,"fork":false,"pushed_at":"2023-11-19T20:52:52.000Z","size":134,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-25T16:25:29.146Z","etag":null,"topics":["dataframe","fast","lxml","multiprocessing","pandas","scraping","web","webscraping"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/lxml2pandas/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hansalemaos.png","metadata":{"files":{"readme":"README.MD","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-10-21T05:56:44.000Z","updated_at":"2023-12-23T20:08:44.000Z","dependencies_parsed_at":"2026-02-23T09:01:05.394Z","dependency_job_id":null,"html_url":"https://github.com/hansalemaos/lxml2pandas","commit_stats":null,"previous_names":["hansalemaos/lxml2pandas"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hansalemaos/lxml2pandas","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hansalemaos%2Flxml2pandas","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hansalemaos%2Flxml2pandas/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hansalemaos%2Flxml2pandas/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hansalemaos%2Flxml2pandas/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hansalemaos","download_url":"https://codeload.github.com/hansalemaos/lxml2pandas/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hansalemaos%2Flxml2pandas/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29740714,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-23T07:44:07.782Z","status":"ssl_error","status_checked_at":"2026-02-23T07:44:07.432Z","response_time":90,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dataframe","fast","lxml","multiprocessing","pandas","scraping","web","webscraping"],"created_at":"2026-02-23T09:00:57.630Z","updated_at":"2026-02-23T09:01:07.607Z","avatar_url":"https://github.com/hansalemaos.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# lxml to pandas for fast web scraping\r\n\r\n## Tested against Windows / Python 3.11 / Anaconda\r\n\r\n## pip install lxml2pandas\r\n\r\n```python\r\nfrom lxml2pandas import subprocess_parsing\r\nfrom PrettyColorPrinter import add_printer\r\n\r\nadd_printer(1)\r\n\r\nhtmldata = [\r\n    (\"bet365\", r\"C:\\Users\\hansc\\Downloads\\bet365 - Apostas Desportivas Online.mhtml\"),\r\n    (\r\n        \"betano\",\r\n        r\"C:\\Users\\hansc\\Downloads\\Brasil Brasileirão - Série A Apostas - Futebol Odds _ Betano.mhtml\",\r\n    ),\r\n    (\"sportingbet\", r\"C:\\Users\\hansc\\Downloads\\Apostas Futebol _ Sportingbet.mhtml\"),\r\n]\r\nallframes = []\r\ndf = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n)\r\n\r\nfor child in df.loc[df.aa_attr_values == \"ovm-Fixture_Container\"].aa_all_children:\r\n    dfr = df.loc[\r\n        df.aa_element_id.isin(child)\r\n        \u0026 (\r\n            (df.aa_attr_values == \"ovm-FixtureDetailsTwoWay_TeamName\")\r\n            | (df.aa_attr_values == \"ovm-ParticipantOddsOnly_Odds\")\r\n        )\r\n    ]\r\n    if len(dfr) == 5:\r\n        print(dfr)\r\n\r\nchi = df.loc[df.aa_attr_values == \"events-list__grid__event\"].aa_all_children\r\nfor c in chi:\r\n    print(\r\n        df.loc[\r\n            (df.aa_element_id.isin(c))\r\n            \u0026 (df.aa_doc_id == \"betano\")\r\n            \u0026 (\r\n                (\r\n                    (df.aa_tag == \"span\")\r\n                    \u0026 (df.aa_attr_values == \"selections__selection__odd\")\r\n                )\r\n                | (\r\n                    (df.aa_tag == \"span\")\r\n                    \u0026 (df.aa_attr_values.str.contains(\"participant-name\", na=False))\r\n                )\r\n            )\r\n        ]\r\n    )\r\n\r\n\r\ndf = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n)\r\n\r\n# pre-filter\r\ndf0 = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n    allowed_tags=(\"span\", \"div\"),\r\n)\r\ndf1 = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n    allowed_tags=(\"span\",),\r\n)\r\ndf2 = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n    allowed_tags=(\"span\", \"div\"),\r\n    allowed_attr=(\r\n        \"ovm-Fixture_Container\",\r\n        \"ovm-FixtureDetailsTwoWay_TeamName\",\r\n        \"ovm-ParticipantOddsOnly_Odds\",\r\n    ),\r\n)\r\n\r\ndf3 = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n    allowed_tags=(),\r\n    allowed_attr=(\"ovm-ParticipantOddsOnly_Odds\",),\r\n    forbidden_tags=(\"p\",),\r\n)\r\n\r\ndf4 = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n    allowed_tags=(),\r\n    allowed_attr=(\r\n        \"ovm-Fixture_Container\",\r\n        \"ovm-FixtureDetailsTwoWay_TeamName\",\r\n        \"ovm-ParticipantOddsOnly_Odds\",\r\n        \"events-list__grid__even\",\r\n        \"selections__selection__odd\",\r\n        \"events-list__grid__info__main__participants__participant-name tw-truncate\",\r\n    ),\r\n    allowed_attr_keys=(\"class\",),\r\n)\r\n\r\n\r\ndf5 = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n    allowed_tags=(),\r\n    allowed_attr=(\"ovm-Fixture_Container\",),\r\n    allowed_attr_keys=(\"class\",),\r\n)\r\n\r\n# parse a webpage:\r\ndf = subprocess_parsing(\r\n    [(\"python\", \"https://www.python.org/\")],\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=True,\r\n    print_stderr=True,\r\n    allowed_tags=(),\r\n    allowed_attr=(),\r\n    allowed_attr_keys=(),\r\n)\r\n\r\n\r\n\r\n# Generate a column with css selectors \r\n\r\nfrom lxml2pandas import subprocess_parsing,pd_add_generate_css_selector\r\npd_add_generate_css_selector()\r\nhtmldata = [\r\n    (\"bet365\", r\"C:\\Users\\hansc\\Downloads\\bet365 - Apostas Desportivas Online2.mhtml\"),\r\n]\r\ndf = subprocess_parsing(\r\n    htmldata,\r\n    chunks=1,\r\n    processes=5,\r\n    fake_header=True,\r\n    print_stdout=False,\r\n    print_stderr=True,\r\n)\r\ndf = df.s_generate_css_selector()\r\n\r\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhansalemaos%2Flxml2pandas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhansalemaos%2Flxml2pandas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhansalemaos%2Flxml2pandas/lists"}