refactor

.gitignore

@@ -1,162 +1,5 @@
-# ---> Python
+driver
-# Byte-compiled / optimized / DLL files
+venv 
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
 *.log
-local_settings.py
+html
-db.sqlite3
+imgs
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-

LICENSE

@@ -1,3 +0,0 @@
-Additional permission under GNU GPL version 3 section 7
-
-If you modify this Program, or any covered work, by linking or combining it with [name of library] (or a modified version of that library), containing parts covered by the terms of [name of library's license], the licensors of this Program grant you additional permission to convey the resulting work. Corresponding Source for a non-source form of such a combination shall include the source code for the parts of [name of library] used as well as that of the covered work.

README.md

@@ -1,2 +0,0 @@
-# PinterestParse
-

main.py

@@ -0,0 +1,64 @@
+from fake_useragent import UserAgent
+from selenium import webdriver
+from selenium.webdriver import Firefox
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.firefox.service import Service
+from selenium.webdriver.firefox.options import Options
+import time
+from datetime import date, datetime
+import os 
+import codecs
+
+
+now = datetime.now()
+formatingDate = now.strftime("%d-%m-%Y-%H-%M")
+
+basePath = "D:\Programming\PythonProgects\PinterestParse\html"
+
+ua = UserAgent(use_cache_server=False)
+#useragent="Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:100.0) Gecko/20100101 Firefox/100.0"
+#useragent=ua
+
+firefoxProfie = r'C:\\Users\\danamir.ASUMADI\\AppData\\Roaming\\Mozilla\\Firefox\\Profiles\\9vfgbpct.default'
+options=Options()
+options.set_preference('profile',firefoxProfie)
+driverPath = os.getcwd()+'\driver\geckodriver.exe'
+service = Service(driverPath)
+browser = Firefox(service=service, options=options)
+
+url = "https://ru.pinterest.com/alexdanamir/%D1%87%D0%B5%D1%80%D1%82%D0%B5%D0%B6%D0%B8/"
+
+browser.get(url)
+
+
+SCROLL_PAUSE_TIME = 5
+
+# Get scroll height
+last_height = browser.execute_script("return document.body.scrollHeight")
+
+while True:
+    # Scroll down to bottom
+    browser.execute_script("window.scrollTo(0, document.body.scrollHeight);")
+
+    # Wait to load page
+    time.sleep(SCROLL_PAUSE_TIME)
+
+    # Calculate new scroll height and compare with last scroll height
+    new_height = browser.execute_script("return document.body.scrollHeight")
+    if new_height == last_height:
+        break
+    last_height = new_height
+
+html = browser.page_source
+
+time.sleep(2) 
+
+htmlName = "pinterest" + "-" + formatingDate + ".txt"
+saveFile = os.path.join(basePath, htmlName)
+
+savedFile = open(saveFile, "w")
+savedFile.write(html)
+savedFile.close()
+browser.close()
+

parsehtml.py

@@ -0,0 +1,22 @@
+import re 
+import os 
+import logging
+
+def main():
+
+    logging.basicConfig(filename='app.log', level=logging.DEBUG)
+
+    basePath = "D:\Programming\PythonProgects\PinterestParse\html"
+
+    fileForParse = os.path.join(basePath,os.listdir(basePath)[0])
+
+    logging.debug(fileForParse)
+
+    openedFile = open(fileForParse, 'r')
+
+    logging.debug(openedFile.read().decode('cp-1251'))
+
+
+
+if __name__ =='__main__':
+    main()