Sourcery Starbot ⭐ refactored wkunzhi/Python3-Spider

【bilibili】自动登录/login.py

@@ -108,11 +108,11 @@ def is_pixel_similar(self, image1, image2, x, y):
         # 阈值 允许误差
         threshold = 10
         # 对比
-        if abs(c_pixel[0] - ic_pixel[0]) < threshold and \
-                abs(c_pixel[1] - ic_pixel[1]) < threshold and \
-                abs(c_pixel[2] - ic_pixel[2]) < threshold:
-            return True
-        return False
+        return (
+            abs(c_pixel[0] - ic_pixel[0]) < threshold
+            and abs(c_pixel[1] - ic_pixel[1]) < threshold
+            and abs(c_pixel[2] - ic_pixel[2]) < threshold
+        )
 
     def get_slice_gap(self, image1, image2):
         """获取缺口的偏移量
@@ -168,12 +168,7 @@ def get_track(self, distance):
         v = 0
 
         while current < distance:
-            if current < mid:
-                # 加速度为正2
-                a = 20
-            else:
-                # 加速度为负3
-                a = -30
+            a = 20 if current < mid else -30
             # 初速度v0
             v0 = v
             # 当前速度v = v0 + at

【bilibili】视频下载/video_download.py

@@ -48,9 +48,9 @@ def get_cid_list(self):
             if not title:
                 title = video_title
             title = re.sub(r'[\/\\:*?"<>|]', '', title)  # 替换为空的
-            print('标题:' + title, 'ID', cid)
+            print(f'标题:{title}', 'ID', cid)
             page = str(item['page'])
-            start_url = start_url + "/?p=" + page
+            start_url = f"{start_url}/?p={page}"
             video_list = down.get_play_list(start_url, cid, quality)
             self.start_time = time.time()
             down.down_video(video_list, title, start_url, page)
@@ -65,20 +65,19 @@ def get_play_list(start_url, cid, quality):
         """
         entropy = 'rbMCKn@KuamXWlPMoJGsKcbiJKUfkPF_8dABscJntvqhRSETg'
         appkey, sec = ''.join([chr(ord(i) + 2) for i in entropy[::-1]]).split(':')
-        params = 'appkey=%s&cid=%s&otype=json&qn=%s&quality=%s&type=' % (appkey, cid, quality, quality)
+        params = f'appkey={appkey}&cid={cid}&otype=json&qn={quality}&quality={quality}&type='
         chksum = hashlib.md5(bytes(params + sec, 'utf8')).hexdigest()
-        url_api = 'https://interface.bilibili.com/v2/playurl?%s&sign=%s' % (params, chksum)
+        url_api = f'https://interface.bilibili.com/v2/playurl?{params}&sign={chksum}'
         headers = {
             'Referer': start_url,
             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
         }
         html = requests.get(url_api, headers=headers).json()
-        video_list = [html['durl'][0]['url']]
-        return video_list
+        return [html['durl'][0]['url']]
 
     def schedule_cmd(self, blocknum, blocksize, totalsize):
         speed = (blocknum * blocksize) / (time.time() - self.start_time)
-        speed_str = " Speed: %s" % self.format_size(speed)
+        speed_str = f" Speed: {self.format_size(speed)}"
         recv_size = blocknum * blocksize
 
         # 设置下载进度条
@@ -95,7 +94,7 @@ def schedule(self, blocknum, blocksize, totalsize):
         """时间表
         """
         speed = (blocknum * blocksize) / (time.time() - self.start_time)
-        speed_str = " Speed: %s" % self.format_size(speed)
+        speed_str = f" Speed: {self.format_size(speed)}"
         recv_size = blocknum * blocksize
 
         # 设置下载进度条
@@ -118,23 +117,17 @@ def format_size(bytes):
         except:
             print("传入的字节格式不对")
             return "Error"
-        if kb >= 1024:
-            M = kb / 1024
-            if M >= 1024:
-                G = M / 1024
-                return "%.3fG" % (G)
-            else:
-                return "%.3fM" % (M)
-        else:
+        if kb < 1024:
             return "%.3fK" % (kb)
+        M = kb / 1024
+        return "%.3fG" % (M / 1024) if M >= 1024 else "%.3fM" % (M)
 
     def down_video(self, video_list, title, start_url, page):
         """下载视频
         """
-        num = 1
         print('正在下载请稍等...'.format(page))
         current_video_path = os.path.join(sys.path[0], 'bilibili下载目录', title)  # 当前目录作为下载目录
-        for i in video_list:
+        for num, i in enumerate(video_list, start=1):
             opener = urllib.request.build_opener()
             # 请求头
             opener.addheaders = [
@@ -154,13 +147,19 @@ def down_video(self, video_list, title, start_url, page):
                 os.makedirs(current_video_path)
             # 开始下载
             if len(video_list) > 1:
-                urllib.request.urlretrieve(url=i,
-                                           filename=os.path.join(current_video_path, r'{}-{}.mp4'.format(title, num)),
-                                           reporthook=self.schedule_cmd)
+                urllib.request.urlretrieve(
+                    url=i,
+                    filename=os.path.join(
+                        current_video_path, f'{title}-{num}.mp4'
+                    ),
+                    reporthook=self.schedule_cmd,
+                )
             else:
-                urllib.request.urlretrieve(url=i, filename=os.path.join(current_video_path, r'{}.mp4'.format(title)),
-                                           reporthook=self.schedule_cmd)
-            num += 1
+                urllib.request.urlretrieve(
+                    url=i,
+                    filename=os.path.join(current_video_path, f'{title}.mp4'),
+                    reporthook=self.schedule_cmd,
+                )
 
     @staticmethod
     def combine_video(video_list, title):
@@ -169,7 +168,7 @@ def combine_video(video_list, title):
         current_video_path = os.path.join(sys.path[0], 'bilibili_video', title)  # 当前目录作为下载目录
         if len(video_list) >= 2:
             # 视频大于一段才要合并
-            print('下载完成,正在合并视频...' + title)
+            print(f'下载完成,正在合并视频...{title}')
             # 定义一个数组
             L = []
             # 访问 video 文件夹 (假设视频都放在这里面)
@@ -187,12 +186,14 @@ def combine_video(video_list, title):
             # 拼接视频
             final_clip = concatenate_videoclips(L)
             # 生成目标视频文件
-            final_clip.to_videofile(os.path.join(root_dir, r'{}.mp4'.format(title)), fps=24, remove_temp=False)
-            print('视频合并完成' + title)
+            final_clip.to_videofile(
+                os.path.join(root_dir, f'{title}.mp4'), fps=24, remove_temp=False
+            )
+            print(f'视频合并完成{title}')
 
         else:
             # 视频只有一段则直接打印下载完成
-            print('视频合并完成:' + title)
+            print(f'视频合并完成:{title}')
 
 
 if __name__ == '__main__':

【双色球】头奖分布/main.py

@@ -38,10 +38,8 @@ def clean_data(self, data):
         清洗数据
         :return:
         """
-        columns = []
-
-        for item in data.get('result'):
-            columns.append([
+        columns = [
+            [
                 item.get('code'),
                 item.get('date'),
                 item.get('week'),
@@ -56,8 +54,9 @@ def clean_data(self, data):
                 item.get('prizegrades')[1].get('typenum'),
                 item.get('prizegrades')[2].get('typemoney'),
                 item.get('prizegrades')[2].get('typenum'),
-            ])
-
+            ]
+            for item in data.get('result')
+        ]
         df = pd.DataFrame(
             columns,
             columns=["期数", "开奖日期", "星期数", "红球", "蓝球", "销售金额", "奖池", "中奖地区", "一等奖金", "一等奖人数", "二等奖金", "二等奖人数", "三等奖金", "三等奖人数"],  # 指定列
@@ -79,8 +78,7 @@ def set_data(self, df):
         for i in df['中奖地区']:
             for addr in i.split(',')[:-1]:
                 name, num = jieba.cut(addr[:-1])
-                for n in range(int(num)):
-                    cut_text.append(name)
+                cut_text.extend(name for _ in range(int(num)))
         print(" ".join(cut_text))
 
         w = wordcloud.WordCloud(font_path=self.font, background_color="white", scale=4)

【壁纸】美女壁纸下载器/bg_down.py

@@ -38,7 +38,7 @@ def down_load(self, file_url, file_full_name, now_photo_count, all_photo_count):
                         all_photo_count), end=" ")
         # 下载完图片后获取图片扩展名，并为其增加扩展名
         file_type = guess(file_full_name)
-        rename(file_full_name, file_full_name + '.' + file_type.extension)
+        rename(file_full_name, f'{file_full_name}.{file_type.extension}')
 
     def crawler_photo(self, type_id, photo_count):
         """
@@ -70,8 +70,8 @@ def crawler_photo(self, type_id, photo_count):
         for photo in photo_data:
 
             # 创建一个文件夹存放我们下载的图片
-            if not exists('./' + str(type_id)):
-                makedirs('./' + str(type_id))
+            if not exists(f'./{str(type_id)}'):
+                makedirs(f'./{str(type_id)}')
 
             # 准备下载的图片链接
             file_url = photo['urls']['raw']
@@ -81,7 +81,7 @@ def crawler_photo(self, type_id, photo_count):
             file_name_only = file_name_only[len(file_name_only) - 1]
 
             # 准备保存到本地的完整路径
-            file_full_name = './' + str(type_id) + '/' + file_name_only
+            file_full_name = f'./{str(type_id)}/{file_name_only}'
 
             # 开始下载图片
             self.down_load(file_url, file_full_name, now_photo_count, all_photo_count)

【大众点评】字体反爬、坐标反爬/旧版/parse_address_poi.py

@@ -35,11 +35,9 @@ def decode(C):
     I = -1
     H = 0
     B = ''
-    J = len(C)
     G = ord(C[-1])
+    J = len(C) - 1
     C = C[:-1]
-    J -= 1
-
     for E in range(J):
         D = int(C[E], cha) - add
         if D >= add:
@@ -51,7 +49,7 @@ def decode(C):
 
     A = int(B[:I], digi)
     F = int(B[I + 1:], digi)
-    L = (A + F - int(G)) / 2
+    L = (A + F - G) / 2
     K = float(F - L) / 100000
     L = float(L) / 100000
     return {'lng': L, 'lat': K}

【大众点评】字体反爬、坐标反爬/旧版/parse_font_css.py

@@ -25,8 +25,7 @@ def get_css(self, html):
         if not svg_text_css:
             raise Exception("未找到链接")
         css_url = svg_text_css.group(1)
-        content = self.parse_url('https:' + css_url)
-        return content
+        return self.parse_url(f'https:{css_url}')
 
     # 获取定义偏移量的css文件后将结果以字典形式存储
     @ staticmethod
@@ -36,21 +35,15 @@ def get_css_offset(content_css):
         :return: {'xxx': ['192', '1550']}
         """
         offset_item = re.findall(r'(\.[a-zA-Z0-9-]+)\{background:-(\d+).0px -(\d+).0px', content_css)
-        result = {}
-        for item in offset_item:
-            css_class = item[0][1:]
-            x_offset = item[1]
-            y_offset = item[2]
-            result[css_class] = [x_offset, y_offset]
-        return result
+        return {item[0][1:]: [item[1], item[2]] for item in offset_item}
 
     # 获取svg url组
     @staticmethod
     def get_svg_url_dict(content_css):
         items = re.findall(r'span\[class\^="(.*?)"\].*?width: (\d+)px;.*?background-image: url\((.*?)\);', content_css)
         result = {}
         for code, size, url in items:
-            svg_list = [int(size), 'https:' + url]
+            svg_list = [int(size), f'https:{url}']
             result[code] = svg_list
         return result
 
@@ -100,7 +93,7 @@ def get_comment_num(self):
                 svg_url = svg[1]
                 new_num = self.parse_comment_css(svg_url, size, x_offset, y_offset)
                 num = num * 10 + int(new_num)
-            print("餐馆: {}, 点评数: {}".format(shop_name, num))
+            print(f"餐馆: {shop_name}, 点评数: {num}")
 
 
 if __name__ == '__main__':

【大众点评】字体反爬、坐标反爬/最新版7月/main.py

@@ -50,8 +50,8 @@ def parse_ttf(self, code):
         result_list = self.r.hmget(HASH_TABLE, self.name_list)  # 取出对应字库表（已修复bug）
         for result in result_list:
             json_data = json.loads(result)
-            if 'uni' + clean_code in json_data:
-                return json_data['uni' + clean_code]
+            if f'uni{clean_code}' in json_data:
+                return json_data[f'uni{clean_code}']
         return False
 
     def add_hash(self, name, json_data):
@@ -86,13 +86,13 @@ def install_ttf(self, ttf_list):
                 # 已存在无需安装
                 continue
             # 安装字体
-            with open(name + '.woff', 'wb+') as f:
-                f.write(requests.get('http://' + ttf_list[index]).content)  # 下载写入
-                font = TTFont(name + '.woff')
+            with open(f'{name}.woff', 'wb+') as f:
+                f.write(requests.get(f'http://{ttf_list[index]}').content)
+                font = TTFont(f'{name}.woff')
                 uni_list = font['cmap'].tables[0].ttFont.getGlyphOrder()  # 取出字形保存到uniList中
                 json_data = json.dumps(dict(zip(uni_list, self.FONT_LIST)), ensure_ascii=False)
                 self.add_hash(name, json_data)
-                os.remove(name + '.woff')  # 用完了删掉，节省资源占用
+                os.remove(f'{name}.woff')
 
     @staticmethod
     def get_ttf_urls(text):

【天眼查】字体加密/tyc.py

@@ -6,6 +6,7 @@
     从网页下载一个字体文件获取对应推导式，动态获取请自行拓展
 """
 
+
 from fontTools.ttLib import TTFont
 import re
 
@@ -15,7 +16,7 @@
     xml = f.read()  # 读取tyc-num.xml赋值给xml
 GlyphID = re.findall(r'<GlyphID id="(.*?)" name="(\d+)"/>', xml)  # 获得对应关系
 print(GlyphID)
-GlyphIDNameLists = list(set([int(Gname) for Gid, Gname in GlyphID])) # 对应关系数量转换
+GlyphIDNameLists = list({int(Gname) for Gid, Gname in GlyphID})
 print(GlyphIDNameLists)
 DigitalDicts = {str(i): str(GlyphIDNameLists[i - 2]) for i in range(2, len(GlyphIDNameLists)+2)}  # 数字对应关系的字典推导式
 print(DigitalDicts)

【抖音】无水印视频解析/parse.py

@@ -11,7 +11,7 @@ class ParseVideo:
 
     def __init__(self, share):
         path = self.get_url(share)
-        self.url = 'https://v.douyin.com/' + path + '/'
+        self.url = f'https://v.douyin.com/{path}/'
         self.headers = {
             'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1',
         }
@@ -25,12 +25,13 @@ def get_url(share_url):
     def go_location(self):
         response = self.session.get(self.url, headers=self.headers)
         self.first_url = response.url
-        result = re.search(r'itemId: "(.*?)",[\s\S]*?uid: "(.*?)",[\s\S]*?authorName: "(.*?)",[\s\S]*?dytk: "(.*?)"',
-                           response.text)
-        return result
+        return re.search(
+            r'itemId: "(.*?)",[\s\S]*?uid: "(.*?)",[\s\S]*?authorName: "(.*?)",[\s\S]*?dytk: "(.*?)"',
+            response.text,
+        )
 
     def go_message(self, ret):
-        url = 'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids=' + ret.group(1) + '&dytk=' + ret.group(4)
+        url = f'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids={ret.group(1)}&dytk={ret.group(4)}'
         response = self.session.get(url, headers=self.headers)
         json_data = json.loads(response.text)
         user_id = ret.group(2)