darius-atlas
/
color-palete-parsers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

init

Browse Source
main
Artem-Darius Weber 4 months ago
commit bf26c308d9
12 changed files with 145067 additions and 0 deletions
Show Stats Download Patch File Download Diff File

8
.idea/.gitignore vendored
Unescape View File

@ -0,0 +1,8 @@
# Default ignored files
/shelf/
/workspace.xml
# Editor-based HTTP Client requests
/httpRequests/
# Datasource local storage ignored files
/dataSources/
/dataSources.local.xml

7
.idea/discord.xml
Unescape View File

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="DiscordProjectSettings">
<option name="show" value="ASK" />
<option name="description" value="" />
</component>
</project>

187
.idea/inspectionProfiles/Project_Default.xml
Unescape View File

@ -0,0 +1,187 @@
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
<inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredPackages">
<value>
<list size="159">
<item index="0" class="java.lang.String" itemvalue="httpx" />
<item index="1" class="java.lang.String" itemvalue="Babel" />
<item index="2" class="java.lang.String" itemvalue="sorted-nearest" />
<item index="3" class="java.lang.String" itemvalue="PyYAML" />
<item index="4" class="java.lang.String" itemvalue="marshmallow" />
<item index="5" class="java.lang.String" itemvalue="executing" />
<item index="6" class="java.lang.String" itemvalue="fisher" />
<item index="7" class="java.lang.String" itemvalue="gradio_client" />
<item index="8" class="java.lang.String" itemvalue="Pygments" />
<item index="9" class="java.lang.String" itemvalue="langchain" />
<item index="10" class="java.lang.String" itemvalue="starlette" />
<item index="11" class="java.lang.String" itemvalue="bleach" />
<item index="12" class="java.lang.String" itemvalue="jupyter_server_terminals" />
<item index="13" class="java.lang.String" itemvalue="soupsieve" />
<item index="14" class="java.lang.String" itemvalue="uvicorn" />
<item index="15" class="java.lang.String" itemvalue="jsonschema" />
<item index="16" class="java.lang.String" itemvalue="terminado" />
<item index="17" class="java.lang.String" itemvalue="comm" />
<item index="18" class="java.lang.String" itemvalue="pydub" />
<item index="19" class="java.lang.String" itemvalue="gunicorn" />
<item index="20" class="java.lang.String" itemvalue="click" />
<item index="21" class="java.lang.String" itemvalue="ipykernel" />
<item index="22" class="java.lang.String" itemvalue="nbconvert" />
<item index="23" class="java.lang.String" itemvalue="attrs" />
<item index="24" class="java.lang.String" itemvalue="contourpy" />
<item index="25" class="java.lang.String" itemvalue="psutil" />
<item index="26" class="java.lang.String" itemvalue="dataclasses-json" />
<item index="27" class="java.lang.String" itemvalue="jedi" />
<item index="28" class="java.lang.String" itemvalue="openai" />
<item index="29" class="java.lang.String" itemvalue="jupyter_server" />
<item index="30" class="java.lang.String" itemvalue="natsort" />
<item index="31" class="java.lang.String" itemvalue="asttokens" />
<item index="32" class="java.lang.String" itemvalue="platformdirs" />
<item index="33" class="java.lang.String" itemvalue="matplotlib" />
<item index="34" class="java.lang.String" itemvalue="pandavro" />
<item index="35" class="java.lang.String" itemvalue="jsonpatch" />
<item index="36" class="java.lang.String" itemvalue="httpcore" />
<item index="37" class="java.lang.String" itemvalue="referencing" />
<item index="38" class="java.lang.String" itemvalue="json5" />
<item index="39" class="java.lang.String" itemvalue="pyfaidx" />
<item index="40" class="java.lang.String" itemvalue="numpy" />
<item index="41" class="java.lang.String" itemvalue="requests" />
<item index="42" class="java.lang.String" itemvalue="fastavro" />
<item index="43" class="java.lang.String" itemvalue="grpcio-reflection" />
<item index="44" class="java.lang.String" itemvalue="jupyter-events" />
<item index="45" class="java.lang.String" itemvalue="websocket-client" />
<item index="46" class="java.lang.String" itemvalue="sqlalchemy2-stubs" />
<item index="47" class="java.lang.String" itemvalue="pysam" />
<item index="48" class="java.lang.String" itemvalue="stack-data" />
<item index="49" class="java.lang.String" itemvalue="methplotlib" />
<item index="50" class="java.lang.String" itemvalue="zipp" />
<item index="51" class="java.lang.String" itemvalue="nest-asyncio" />
<item index="52" class="java.lang.String" itemvalue="tenacity" />
<item index="53" class="java.lang.String" itemvalue="mmh3" />
<item index="54" class="java.lang.String" itemvalue="prompt-toolkit" />
<item index="55" class="java.lang.String" itemvalue="linkify-it-py" />
<item index="56" class="java.lang.String" itemvalue="websockets" />
<item index="57" class="java.lang.String" itemvalue="ipywidgets" />
<item index="58" class="java.lang.String" itemvalue="pyarrow" />
<item index="59" class="java.lang.String" itemvalue="watchfiles" />
<item index="60" class="java.lang.String" itemvalue="tornado" />
<item index="61" class="java.lang.String" itemvalue="aiofiles" />
<item index="62" class="java.lang.String" itemvalue="jsonpointer" />
<item index="63" class="java.lang.String" itemvalue="Send2Trash" />
<item index="64" class="java.lang.String" itemvalue="plotly" />
<item index="65" class="java.lang.String" itemvalue="overrides" />
<item index="66" class="java.lang.String" itemvalue="python-multipart" />
<item index="67" class="java.lang.String" itemvalue="toml" />
<item index="68" class="java.lang.String" itemvalue="mistune" />
<item index="69" class="java.lang.String" itemvalue="pandas" />
<item index="70" class="java.lang.String" itemvalue="importlib-resources" />
<item index="71" class="java.lang.String" itemvalue="toolz" />
<item index="72" class="java.lang.String" itemvalue="mpmath" />
<item index="73" class="java.lang.String" itemvalue="pyranges" />
<item index="74" class="java.lang.String" itemvalue="debugpy" />
<item index="75" class="java.lang.String" itemvalue="argon2-cffi" />
<item index="76" class="java.lang.String" itemvalue="yarl" />
<item index="77" class="java.lang.String" itemvalue="pytz" />
<item index="78" class="java.lang.String" itemvalue="moreorless" />
<item index="79" class="java.lang.String" itemvalue="Pillow" />
<item index="80" class="java.lang.String" itemvalue="notebook_shim" />
<item index="81" class="java.lang.String" itemvalue="traitlets" />
<item index="82" class="java.lang.String" itemvalue="bowler" />
<item index="83" class="java.lang.String" itemvalue="protobuf" />
<item index="84" class="java.lang.String" itemvalue="rfc3339-validator" />
<item index="85" class="java.lang.String" itemvalue="arrow" />
<item index="86" class="java.lang.String" itemvalue="mypy" />
<item index="87" class="java.lang.String" itemvalue="python-dotenv" />
<item index="88" class="java.lang.String" itemvalue="nbclient" />
<item index="89" class="java.lang.String" itemvalue="partd" />
<item index="90" class="java.lang.String" itemvalue="MarkupSafe" />
<item index="91" class="java.lang.String" itemvalue="locket" />
<item index="92" class="java.lang.String" itemvalue="tinycss2" />
<item index="93" class="java.lang.String" itemvalue="httptools" />
<item index="94" class="java.lang.String" itemvalue="frozenlist" />
<item index="95" class="java.lang.String" itemvalue="appdirs" />
<item index="96" class="java.lang.String" itemvalue="python-json-logger" />
<item index="97" class="java.lang.String" itemvalue="semantic-version" />
<item index="98" class="java.lang.String" itemvalue="filelock" />
<item index="99" class="java.lang.String" itemvalue="jupyterlab-widgets" />
<item index="100" class="java.lang.String" itemvalue="pyzmq" />
<item index="101" class="java.lang.String" itemvalue="certifi" />
<item index="102" class="java.lang.String" itemvalue="anyio" />
<item index="103" class="java.lang.String" itemvalue="Markdown" />
<item index="104" class="java.lang.String" itemvalue="sympy" />
<item index="105" class="java.lang.String" itemvalue="uvloop" />
<item index="106" class="java.lang.String" itemvalue="notebook" />
<item index="107" class="java.lang.String" itemvalue="beautifulsoup4" />
<item index="108" class="java.lang.String" itemvalue="isoduration" />
<item index="109" class="java.lang.String" itemvalue="jupyter-lsp" />
<item index="110" class="java.lang.String" itemvalue="fqdn" />
<item index="111" class="java.lang.String" itemvalue="jupyter_client" />
<item index="112" class="java.lang.String" itemvalue="orjson" />
<item index="113" class="java.lang.String" itemvalue="jupyterlab_server" />
<item index="114" class="java.lang.String" itemvalue="altair" />
<item index="115" class="java.lang.String" itemvalue="feast" />
<item index="116" class="java.lang.String" itemvalue="fonttools" />
<item index="117" class="java.lang.String" itemvalue="mdit-py-plugins" />
<item index="118" class="java.lang.String" itemvalue="widgetsnbextension" />
<item index="119" class="java.lang.String" itemvalue="charset-normalizer" />
<item index="120" class="java.lang.String" itemvalue="uc-micro-py" />
<item index="121" class="java.lang.String" itemvalue="biopython" />
<item index="122" class="java.lang.String" itemvalue="dask" />
<item index="123" class="java.lang.String" itemvalue="ffmpy" />
<item index="124" class="java.lang.String" itemvalue="langsmith" />
<item index="125" class="java.lang.String" itemvalue="numexpr" />
<item index="126" class="java.lang.String" itemvalue="gradio" />
<item index="127" class="java.lang.String" itemvalue="webcolors" />
<item index="128" class="java.lang.String" itemvalue="async-timeout" />
<item index="129" class="java.lang.String" itemvalue="SQLAlchemy" />
<item index="130" class="java.lang.String" itemvalue="sklearn" />
<item index="131" class="java.lang.String" itemvalue="cloudpickle" />
<item index="132" class="java.lang.String" itemvalue="wcwidth" />
<item index="133" class="java.lang.String" itemvalue="jupyter_core" />
<item index="134" class="java.lang.String" itemvalue="importlib-metadata" />
<item index="135" class="java.lang.String" itemvalue="rfc3986-validator" />
<item index="136" class="java.lang.String" itemvalue="typeguard" />
<item index="137" class="java.lang.String" itemvalue="ncls" />
<item index="138" class="java.lang.String" itemvalue="jsonschema-specifications" />
<item index="139" class="java.lang.String" itemvalue="rpds-py" />
<item index="140" class="java.lang.String" itemvalue="uri-template" />
<item index="141" class="java.lang.String" itemvalue="fissix" />
<item index="142" class="java.lang.String" itemvalue="urllib3" />
<item index="143" class="java.lang.String" itemvalue="jupyterlab" />
<item index="144" class="java.lang.String" itemvalue="Cython" />
<item index="145" class="java.lang.String" itemvalue="six" />
<item index="146" class="java.lang.String" itemvalue="pyTelegramBotAPI" />
<item index="147" class="java.lang.String" itemvalue="nbformat" />
<item index="148" class="java.lang.String" itemvalue="ipython" />
<item index="149" class="java.lang.String" itemvalue="dill" />
<item index="150" class="java.lang.String" itemvalue="volatile" />
<item index="151" class="java.lang.String" itemvalue="fastjsonschema" />
<item index="152" class="java.lang.String" itemvalue="prometheus-client" />
<item index="153" class="java.lang.String" itemvalue="tqdm" />
<item index="154" class="java.lang.String" itemvalue="fastapi" />
<item index="155" class="java.lang.String" itemvalue="proto-plus" />
<item index="156" class="java.lang.String" itemvalue="aiohttp" />
<item index="157" class="java.lang.String" itemvalue="grpcio" />
<item index="158" class="java.lang.String" itemvalue="async-lru" />
</list>
</value>
</option>
</inspection_tool>
<inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
<option name="ignoredErrors">
<list>
<option value="N803" />
</list>
</option>
</inspection_tool>
<inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredIdentifiers">
<list>
<option value="random.random.choice" />
</list>
</option>
</inspection_tool>
</profile>
</component>

6
.idea/inspectionProfiles/profiles_settings.xml
Unescape View File

@ -0,0 +1,6 @@
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>

8
.idea/klfasdkfdsklf.iml
Unescape View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="inheritedJdk" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

7
.idea/misc.xml
Unescape View File

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="MarkdownSettingsMigration">
<option name="stateVersion" value="1" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (klfasdkfdsklf)" project-jdk-type="Python SDK" />
</project>

8
.idea/modules.xml
Unescape View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/klfasdkfdsklf.iml" filepath="$PROJECT_DIR$/.idea/klfasdkfdsklf.iml" />
</modules>
</component>
</project>

6
.idea/vcs.xml
Unescape View File

@ -0,0 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="$PROJECT_DIR$" vcs="Git" />
</component>
</project>

142350
color_palettes.csv
View File

File diff suppressed because it is too large Load Diff

2416
example.csv
View File

File diff suppressed because it is too large Load Diff

61
main.py
Unescape View File

@ -0,0 +1,61 @@
import requests
from bs4 import BeautifulSoup
import csv
from tqdm import tqdm
# Базовый URL для страниц палитр
base_url = "https://www.color-hex.com/color-palettes/?page="
# Количество страниц, которые нужно парсить
total_pages = 1780
output_file = "color_palettes.csv"
with open(output_file, mode='w', newline='', encoding='utf-8') as file:
writer = csv.writer(file)
# Заголовки CSV
headers = ['Palette Category', 'Palette Name'] + [f"Color {i + 1}" for i in range(448)]
writer.writerow(headers)
for page in tqdm(range(1, total_pages + 1), desc="Parsing pages", unit="page"):
# Формируем URL для текущей страницы
url = f"{base_url}{page}"
response = requests.get(url)
if response.status_code == 200:
soup = BeautifulSoup(response.content, 'html.parser')
# Ищем все контейнеры палитр
palettes = soup.find_all('div', class_='palettecontainerlist')
# Проходим по каждой палитре и собираем информацию
for palette in palettes:
# Ищем ссылку с названием палитры (тег <a>)
title_tag = palette.find('a')
palette_name = title_tag['title'] if title_tag else 'No title'
palette_category = "Default Category"
# Ищем все div с цветами внутри палитры
color_divs = palette.find_all('div', class_='palettecolordiv')
color_codes = []
# Извлекаем цвета из атрибута style
for div in color_divs:
style = div['style']
# Ищем hex-код цвета в стиле
color_code = style.split('background-color:')[1].replace(';', '').strip()
color_codes.append(color_code)
# Заполняем недостающие ячейки пустыми значениями, если цветов меньше 448
while len(color_codes) < 448:
color_codes.append('')
writer.writerow([palette_category, palette_name] + color_codes)
else:
print(f"Ошибка при запросе страницы {page}: {response.status_code}")
print(f"Парсинг завершён. Данные записаны в файл {output_file}")

3
requirements.txt
Unescape View File

@ -0,0 +1,3 @@
requests==2.31.0
beautifulsoup4==4.12.2
tqdm==4.66.1
Write Preview
Loading…
Cancel
Save