reyfetch 1.0.35__py3-none-any.whl

reyfetch/rgeneral.py

@@ -0,0 +1,158 @@
+# !/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+@Time    : 2024-01-10 21:57:08
+@Author  : Rey
+@Contact : reyxbo@163.com
+@Explain : General methods.
+"""
+
+
+from json import loads as json_loads
+from reykit.rnet import request
+from reykit.rre import search
+from reykit.rtime import now
+
+
+__all__ = (
+    'crawl_calendar',
+    'crawl_lunar_calendar'
+)
+
+
+def crawl_calendar(
+    year: int | None = None,
+    month: int | None = None
+) -> list[dict]:
+    """
+    Crawl Baidu Web calendar table.
+
+    Parameters
+    ----------
+    year : Given year.
+        - `None`: Now year.
+    month : Given month.
+        - `None`: Now month.
+
+    Returns
+    -------
+    Calendar table.
+    """
+
+    # Get parameter.
+    now_date = now('date')
+    year = year or now_date.year
+    month = month or now_date.month
+    if month == 12:
+        month = 1
+    else:
+        month += 1
+    url = 'https://opendata.baidu.com/data/inner'
+    query = '%s年%s月' % (year, month)
+    params = {
+        'tn': 'reserved_all_res_tn',
+        'type': 'json',
+        'resource_id': '52109',
+        'query': query,
+        'apiType': 'yearMonthData',
+        'cb': 'jsonp_1706670926975_94318'
+    }
+
+    # Request.
+    response = request(url, params)
+
+    # Extract.
+    pattern = '{.+}'
+    text = search(pattern, response.text)
+    data: dict = json_loads(text)
+    table: list[dict] = data['Result'][0]['DisplayData']['resultData']['tplData']['data']['almanac']
+
+    # Convert.
+    week_dict = {
+        '一': 0,
+        '二': 1,
+        '三': 2,
+        '四': 3,
+        '五': 4,
+        '六': 5,
+        '日': 6
+    }
+    table = [
+        {
+            'year': int(row['year']),
+            'month': int(row['month']),
+            'day': int(row['day']),
+            'week': week_dict[row['cnDay']],
+            'work': row.get('status'),
+            'festival': [
+                {
+                    'name': info['name'],
+                    'url': info.get('baikeUrl')
+                }
+                for info in row.get('festivalInfoList', [])
+            ],
+            'animal': row['animal'],
+            'lunar_year': int(row['lunarYear']),
+            'lunar_month': int(row['lunarMonth']),
+            'lunar_day': int(row['lunarDate']),
+            'gz_year': row['gzYear'],
+            'gz_month': row['gzMonth'],
+            'gz_day': row['gzDate'],
+            'suit': row['suit'].split('.'),
+            'avoid': row['avoid'].split('.'),
+            'url': row['yjJumpUrl']
+        }
+        for row in table
+    ]
+    for row in table:
+        week = row['week']
+        work = row['work']
+        match work:
+            case None:
+                is_work_day = week not in (5, 6)
+            case '1':
+                is_work_day = False
+            case '2':
+                is_work_day = True
+        row['work'] = is_work_day
+
+    return table
+
+
+def crawl_lunar_calendar(
+    year: int | None = None,
+    month: int | None = None
+) -> list[dict]:
+    """
+    Crawl Rili Web lunar calendar table.
+
+    Parameters
+    ----------
+    year : Given year.
+        - `None`: Now year.
+    month : Given month.
+        - `None`: Now month.
+
+    Returns
+    -------
+    Lunar calendar table.
+    """
+
+    # Get parameter.
+    now_date = now('date')
+    year = year or now_date.year
+    month = month or now_date.month
+    url = 'https://www.rili.com.cn/rili/json/pc_wnl/%s/%02d.js' % (year, month)
+    params = {'_': now('timestamp')}
+
+    # Request.
+    response = request(url, params)
+
+    # Extract.
+    pattern = '{.+}'
+    text = search(pattern, response.text)
+    data = json_loads(text)
+    table = data['data']
+
+    return table

reyfetch/rsina.py

@@ -0,0 +1,239 @@
+# !/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+@Time    : 2024-01-22 14:06:05
+@Author  : Rey
+@Contact : reyxbo@163.com
+@Explain : Sina Web fetch methods.
+"""
+
+
+from typing import TypedDict, Literal
+from reykit.rbase import throw
+from reykit.rnet import request
+from reykit.rre import search, findall, sub
+from reykit.rtime import now
+
+
+__all__ = (
+    'crawl_sina_search_market',
+    'crawl_sina_stock_info'
+)
+
+
+SinaStockInfo = TypedDict(
+    'SinaStockInfo',
+    {
+        'code': str,
+        'name': str,
+        'price': float,
+        'open': float,
+        'pre_close': float,
+        'high': float,
+        'low': float,
+        'volume': int,
+        'amount': int,
+        'time': str,
+        'url': str,
+        'change': float,
+        'change_rate': float,
+        'swing': float
+    }
+)
+
+
+def crawl_sina_search_market(keyword: str) -> list[dict[Literal['code', 'name', 'type', 'url'], str]]:
+    """
+    Crawl Sina Web and search market product table.
+
+    Parameters
+    ----------
+    keyword : Search keyword.
+
+    Returns
+    -------
+    Search result table.
+    """
+
+    # Parameter.
+    url = 'https://biz.finance.sina.com.cn/suggest/lookup_n.php'
+    params = {
+        'country': '',
+        'q': keyword
+    }
+
+    # Request.
+    response = request(
+        url,
+        params,
+        check=True
+    )
+
+    # Unique result.
+    if response.request.url.startswith("https://finance.sina.com.cn"):
+        pattern = "var papercode = '(.+?)'"
+        stock_code = search(pattern, response.text)
+        pattern = "var stockname = '(.+?)'"
+        stock_name = search(pattern, response.text)
+        row = {
+            'code': stock_code,
+            'name': stock_name,
+            'type': '沪深股市(个股)',
+            'url': response.request.url
+        }
+        table = [row]
+        return table
+
+    # Extract.
+    pattern = '<div class="(market|list)"(.+?)</div>'
+    labels_result: tuple[str, str] = findall(pattern, response.text)
+    table = []
+    for index, (label_class, div_text) in enumerate(labels_result):
+        if label_class != 'list':
+            continue
+        stock_type_div_text = labels_result[index - 1][1]
+        stock_type = stock_type_div_text.rsplit('<div>', 1)[1]
+        pattern = '<label><a href="([^"]+)" target="_blank">(.+?)</label>'
+        stocks_result = findall(pattern, div_text)
+        for stock_url, stock_text in stocks_result:
+            pattern = '<.+?>'
+            stock_info = sub(pattern, stock_text)
+            stock_info_split = stock_info.split(maxsplit=1)
+            if len(stock_info_split) != 2:
+                continue
+            stock_code, stock_name = stock_info_split
+            if stock_name.startswith('('):
+                stock_name = stock_name[1:-1]
+            row = {
+                'code': stock_code,
+                'name': stock_name,
+                'type': stock_type,
+                'url': stock_url
+            }
+            table.append(row)
+
+    return table
+
+
+def crawl_sina_stock_info(code: str | list[str]) -> list[SinaStockInfo]:
+    """
+    Crawl Sina Web stock information.
+
+    Parameters
+    ----------
+    code : Stock code.
+
+    Returns
+    -------
+    Stock information table.
+    """
+
+    # Parameter.
+    if type(code) == str:
+        code = code.split(',')
+    code = [
+        (
+            i
+            if i[-1] in '0123456789'
+            else 'gb_' + i.replace('.', '$')
+        )
+        for i in code
+    ]
+    code = ','.join(code)
+    code = code.lower()
+    url = 'https://hq.sinajs.cn/rn=%s&list=%s' % (
+        now('timestamp'),
+        code
+    )
+    headers = {'Referer': 'https://finance.sina.com.cn'}
+
+    # Request.
+    response = request(
+        url,
+        headers=headers,
+        check=True
+    )
+
+    # Extract.
+    pattern = '([^_]+?)="([^"]*)"'
+    result: list[tuple[str, str]] = findall(pattern, response.text)
+    table = []
+    for code, info in result:
+        info_list = info.split(',')
+        info_list_len = len(info_list)
+        match info_list_len:
+
+            ## A.
+            case 34:
+                (
+                    stock_name,
+                    stock_open,
+                    stock_pre_close,
+                    stock_price,
+                    stock_high,
+                    stock_low,
+                    _,
+                    _,
+                    stock_volume,
+                    stock_amount,
+                    *_,
+                    stock_date,
+                    stock_time,
+                    _,
+                    _
+                ) = info_list
+                row = {
+                    'code': code,
+                    'name': stock_name,
+                    'price': float(stock_price),
+                    'open': float(stock_open),
+                    'pre_close': float(stock_pre_close),
+                    'high': float(stock_high),
+                    'low': float(stock_low),
+                    'volume': int(float(stock_volume)),
+                    'amount': int(float(stock_amount)),
+                    'time': '%s %s' % (stock_date, stock_time),
+                    'url': 'https://finance.sina.com.cn/realstock/company/%s/nc.shtml' % code
+                }
+
+            # US.
+            case 36 | 30:
+                (
+                    stock_name,
+                    stock_price,
+                    _,
+                    stock_date_time,
+                    _,
+                    stock_open,
+                    stock_high,
+                    stock_low,
+                    _, _,
+                    stock_amount,
+                    _, _, _, _, _, _, _, _, _, _, _, _, _, _, _,
+                    stock_pre_close,
+                    *_
+                ) = info_list
+                row = {
+                    'code': code,
+                    'name': stock_name,
+                    'price': float(stock_price),
+                    'open': float(stock_open),
+                    'pre_close': float(stock_pre_close),
+                    'high': float(stock_high),
+                    'low': float(stock_low),
+                    'amount': int(float(stock_amount)),
+                    'time': stock_date_time,
+                    'url': 'https://stock.finance.sina.com.cn/usstock/quotes/%s.html' % code.replace('$', '.')
+                }
+
+            ## Throw exception.
+            case _:
+                throw(AssertionError, info)
+
+        row['change'] = round(row['price'] - row['pre_close'], 4)
+        row['change_rate'] = round(row['change'] / row['pre_close'] * 100, 4)
+        row['swing'] = round((row['high'] - row['low']) / row['high'] * 100, 4)
+        table.append(row)
+
+    return table

reyfetch/rtoutiao.py

@@ -0,0 +1,71 @@
+# !/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+@Time    : 2024-01-22 14:06:05
+@Author  : Rey
+@Contact : reyxbo@163.com
+@Explain : Toutiao Web fetch methods.
+"""
+
+
+from typing import Any, Literal
+from reykit.rnet import request
+
+
+__all__ = (
+    'crawl_toutiao_hot_search',
+)
+
+
+def crawl_toutiao_hot_search() -> list[dict[Literal['title', 'type', 'label', 'hot', 'url', 'image'], Any]]:
+    """
+    Crawl Toutiao Web hot search table.
+
+    Returns
+    -------
+    Hot search table.
+        - `Key 'title'`: Hot search title.
+        - `Key 'type'`: Hot search type list.
+        - `Key 'label'`: Hot search label.
+        - `Key 'hot'`: Hot search hot value.
+        - `Key 'url'`: Hot search URL.
+        - `Key 'image'`: Hot search image URL.
+    """
+
+    # Request.
+    url = 'https://www.toutiao.com/hot-event/hot-board/'
+    params = {'origin': 'toutiao_pc'}
+    response = request(
+        url,
+        params,
+        check=True
+    )
+
+    # Extract.
+    response_json = response.json()
+    table: list[dict] = response_json['data']
+
+    # Convert.
+    table = [
+        {
+            'title': info['Title'],
+            'type': info.get('InterestCategory'),
+            'label': info.get('LabelDesc'),
+            'hot': int(info['HotValue']),
+            'url': info['Url'],
+            'image': info['Image']['url'],
+        }
+        for info in table
+    ]
+    sort_key = lambda row: row['hot']
+    table.sort(key=sort_key, reverse=True)
+    table = [
+        {
+            'rank': index,
+            **row
+        }
+        for index, row in enumerate(table)
+    ]
+
+    return table

reyfetch/rweibo.py

@@ -0,0 +1,90 @@
+# !/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+@Time    : 2024-01-22 14:06:05
+@Author  : Rey
+@Contact : reyxbo@163.com
+@Explain : Weibo Web fetch methods.
+"""
+
+
+from typing import Any, Literal
+from fake_useragent import UserAgent
+from reykit.rnet import request, join_url
+from reykit.rtime import now
+
+
+__all__ = (
+    'crawl_weibo_hot_search',
+)
+
+
+def crawl_weibo_hot_search() -> list[dict[Literal['rank', 'time', 'title', 'type', 'hot', 'url'], Any]]:
+    """
+    Crawl Weibo Web hot search table.
+
+    Returns
+    -------
+    Hot search table.
+        - `Key 'rank'`: Hot search rank.
+        - `Key 'time'`: Hot search time.
+        - `Key 'title'`: Hot search title.
+        - `Key 'type'`: Hot search type.
+        - `Key 'hot'`: Hot search hot value.
+        - `Key 'url'`: Hot search URL.
+    """
+
+    # Request.
+    url = 'https://weibo.com/ajax/side/searchBand'
+    timestamp_second = now('timestamp_s')
+    params = {
+        'type': 'hot',
+        'last_tab': 'hot',
+        'last_table_time': timestamp_second
+    }
+    ua = UserAgent()
+    headers = {
+        'cookie': (
+            'SUB=_2AkMf61vxf8NxqwFRmvgTzm_la4RxzAvEieKpt6oqJRMxHRl-yT9yqmIEtRB6NGt1HrGel2jwtm1TPoj0LB2qbH5Djjty; '
+            'SUBP=0033WrSXqPxfM72-Ws9jqgMF55529P9D9W5LjsD9P67XdiTS.eBzcX8n; '
+            'XSRF-TOKEN=JUL_aQ7hlSuI98dYZDxZdYNV; '
+            'WBPSESS=9-DrhgMbGnVf8No6y5BLAa-AdtUBbe2eTM9RR6Vd3EQO6R5LLxnh_NKkxuJ_a9m2rFeEEGrQEIgK1oe4gs2SnXWX_ZT5_XC9csUnNHL-q-ZJLzj9wbKvtMB4ZYVnfrM8'
+        ),
+        'referer': 'https://weibo.com/newlogin?tabtype=weibo&gid=102803&openLoginLayer=0&url=https%3A%2F%2Fwww.weibo.com%2F',
+        'user-agent': ua.edge,
+    }
+    response = request(url, params, headers=headers, check=True)
+
+    # Extract.
+    response_json = response.json()
+    table: list[dict] = response_json['data']['realtime']
+
+    # Convert.
+    table = [
+        {
+            'title': info['word'],
+            'hot': info['num'],
+            'url': join_url(
+                'https://s.weibo.com/weibo',
+                {'q': '#%s#' % info['word']}
+            )
+        }
+        for info in table
+        if 'flag' in info
+    ]
+    sort_key = lambda row: (
+        0
+        if row['hot'] is None
+        else row['hot']
+    )
+    table.sort(key=sort_key, reverse=True)
+    table = [
+        {
+            'rank': index,
+            **row
+        }
+        for index, row in enumerate(table)
+    ]
+
+    return table

reyfetch-1.0.35.dist-info/METADATA

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: reyfetch
+Version: 1.0.35
+Summary: Web data fetch method set.
+Project-URL: homepage, https://github.com/reyxbo/reyfetch/
+Author-email: Rey <reyxbo@163.com>
+License: Copyright 2025 ReyXBo
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+License-File: LICENSE
+Keywords: crawl Web,fetch,request API,rey,reyxbo
+Requires-Python: >=3.12
+Requires-Dist: fake-useragent
+Requires-Dist: reykit
+Requires-Dist: selenium
+Description-Content-Type: text/markdown
+
+# reyfetch
+
+> Web data fetch method set.
+
+## Install
+
+```
+pip install reyfetch
+```

reyfetch-1.0.35.dist-info/RECORD

@@ -0,0 +1,14 @@
+reyfetch/__init__.py,sha256=gDkQmFLZGToSqb1HVfvGxvc9t3mt8slg7_MVc44llns,484
+reyfetch/rali.py,sha256=fdwraDilYcSnsCdV3FaLAT_g-legTufm0H73x8OQkx0,33667
+reyfetch/rall.py,sha256=86TMZiNsv-UinZ2L3_m3ugTHekUWnfVlWMedte0MOwQ,350
+reyfetch/rbaidu.py,sha256=vwVHiWxeaKnklGcORH2b4njmnmtAdWclSqDdJFNRirY,14023
+reyfetch/rbase.py,sha256=Q9FldtjDHy3GSgGBv1qzheFKVBnQB9UvwFswbv6dQDA,5021
+reyfetch/rdouban.py,sha256=X2wGolwPiYXHBJj06_u2dfNSKDtB68qJQvmij1ysUn8,19372
+reyfetch/rgeneral.py,sha256=s270rtlVv1owkGF57Tjs8Oc5bJRD_XtWISpKlEJ7mbE,3797
+reyfetch/rsina.py,sha256=WONT6NN67seYjlvXZ39RbibticdDAuauGk6SAvtdEq8,6889
+reyfetch/rtoutiao.py,sha256=zLPnf2_XSC0d2RZgtMVoVyWpA2UDGNXYpRjYi3DGabI,1671
+reyfetch/rweibo.py,sha256=T58q6wOv0p7j6WBH4we5k9x8IgFhQN__wqsqTHYMbmU,2522
+reyfetch-1.0.35.dist-info/METADATA,sha256=JF2TLmNHfJ1mv5LHy8wIn6CvyV91RmP2bGA0SRFI9Mw,1589
+reyfetch-1.0.35.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+reyfetch-1.0.35.dist-info/licenses/LICENSE,sha256=UYLPqp7BvPiH8yEZduJqmmyEl6hlM3lKrFIefiD4rvk,1059
+reyfetch-1.0.35.dist-info/RECORD,,

reyfetch-1.0.35.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.27.0
+Root-Is-Purelib: true
+Tag: py3-none-any

reyfetch-1.0.35.dist-info/licenses/LICENSE

@@ -0,0 +1,7 @@
+Copyright 2025 ReyXBo
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.