Merge pull request #20 from blacknon/develop

Version 1.1.7

pydork/engine_common.py

@@ -13,7 +13,6 @@
 import requests
 import os
 import pickle
-import time
 
 # selenium driver auto install packages
 import chromedriver_autoinstaller
@@ -575,11 +574,12 @@ def get_result(self, url: str, method='GET', data=None):
  if self.USE_SELENIUM:
  result = self.request_selenium(url, method=method, data=data)
 
- for i in range(0, 10):
- self.driver.execute_script(
- "window.scrollTo(0,document.body.scrollHeight)"
- )
- time.sleep(3)
+ # NOTE: seleniumでのブラウザスクロール. googleでの処理で不要になったため、ただ遅くなるだけで不便なので一旦コメントアウト.
+ # for i in range(0, 10):
+ # self.driver.execute_script(
+ # "window.scrollTo(0,document.body.scrollHeight)"
+ # )
+ # time.sleep(0.5)
 
  # 優先度2: Splash経由でのアクセス(Seleniumが有効になってない場合はこちら)
  elif self.USE_SPLASH:
@@ -705,14 +705,35 @@ def get_text_links(self, soup: BeautifulSoup):
  list: textの検索結果([xxx,xxx,xxx...])
  """
  # linkのurlを取得する
+ self.MESSAGE.print_text(
+ self.SOUP_SELECT_URL, # type: ignore
+ header=self.MESSAGE.HEADER + ': ' + \
+ Color.GREEN + '[get_text_link.SOUP_SELECT_URL]' + Color.END,
+ separator=" :",
+ mode="debug",
+ )
  elements = soup.select(self.SOUP_SELECT_URL)
  elinks = [e['href'] for e in elements]
 
  # linkのtitleを取得する
+ self.MESSAGE.print_text(
+ self.SOUP_SELECT_TITLE, # type: ignore
+ header=self.MESSAGE.HEADER + ': ' + \
+ Color.GREEN + '[get_text_link.SOUP_SELECT_TITLE]' + Color.END,
+ separator=" :",
+ mode="debug",
+ )
  elements = soup.select(self.SOUP_SELECT_TITLE)
  etitles = [e.text for e in elements]
 
  # linkのtextを取得する
+ self.MESSAGE.print_text(
+ self.SOUP_SELECT_TEXT, # type: ignore
+ header=self.MESSAGE.HEADER + ': ' + \
+ Color.GREEN + '[get_text_link.SOUP_SELECT_TEXT]' + Color.END,
+ separator=" :",
+ mode="debug",
+ )
  elements = soup.select(self.SOUP_SELECT_TEXT)
  etext = [e.text for e in elements]
 

pydork/engine_google.py

@@ -202,16 +202,16 @@ def get_links(self, url: str, html: str, type: str):
 
  # Selenium経由、かつFirefoxを使っている場合
  if self.USE_SELENIUM:
- self.SOUP_SELECT_URL = '.yuRUbf > div > a'
- self.SOUP_SELECT_TITLE = '.yuRUbf > div > a > .LC20lb'
- self.SOUP_SELECT_TEXT = '.lEBKkf'
+ self.SOUP_SELECT_URL = '.yuRUbf > div > span > a'
+ self.SOUP_SELECT_TITLE = '.yuRUbf > div > span > a > h3'
+ self.SOUP_SELECT_TEXT = '.yXK7lf'
  self.SOUP_SELECT_NEXT_URL = '.AaVjTc > tbody > tr > td > a'
 
  # Splash経由で通信している場合
  elif self.USE_SPLASH:
- self.SOUP_SELECT_URL = '.yuRUbf > a'
- self.SOUP_SELECT_TITLE = '.yuRUbf > a > .LC20lb'
- self.SOUP_SELECT_TEXT = '.lEBKkf'
+ self.SOUP_SELECT_URL = '.yuRUbf > div > span > a.href'
+ self.SOUP_SELECT_TITLE = '.yuRUbf > div > span > a > h3'
+ self.SOUP_SELECT_TEXT = '.yXK7lf'
  self.SOUP_SELECT_NEXT_URL = '.AaVjTc > tbody > tr > td > a'
 
  # TODO: SEARCH_NEXT_URLを書き換える

setup.py

@@ -27,7 +27,6 @@
 
 # 補完ファイルインストール用関数
 def get_data_files():
-
  # 補完ファイルのインストール先を取得する関数
  def get_completefile_install_location(shell):
  # pathのprefixを定義
@@ -78,12 +77,13 @@ def get_completefile_install_location(shell):
  data_files = []
  data_files.append((loc['bash'], files['bash']))
  data_files.append((loc['zsh'], files['zsh']))
+
  return data_files
 
 
 name = 'pydork'
-version = '1.1.6'
-release = '1.1.6'
+version = '1.1.7'
+release = '1.1.7'
 
 if __name__ == "__main__":
  setuptools.setup(
@@ -126,6 +126,7 @@ def get_completefile_install_location(shell):
  'Programming Language :: Python :: 3.8',
  'Programming Language :: Python :: 3.9',
  'Programming Language :: Python :: 3.10',
+ 'Programming Language :: Python :: 3.11',
  'License :: OSI Approved :: MIT License',
  ],
  data_files=get_data_files(),