def is_excluded(email):
source_file = os.path.join(get_current_dir(), INIT_PATH_PARTICLE, "excluded_emails.txt")
with open(source_file, "r") as f:
excluded_emails = [line.rstrip('\n') for line in f]
return email in excluded_emails
def parse_phrase_bunch(phrases):
global phrase_counter
logs_dir = os.path.join(get_current_dir(), "log")
# clear_files(logs_dir)
try:
driver = get_driver()
used_email = handle_login(driver)
driver.get("https://tools.pixelplus.ru/tools/geo")
email_log = get_log_path("email_log.txt")
# phrase, write_mode, enc, full_path_to_file
write_phrase_to_log(used_email, 'a', ENC, email_log)
handle_phrases(phrases, driver)
index_log = get_log_path("index_log.txt")
write_phrase_to_log(phrase_counter, 'w', ENC, index_log)
phrase_counter += PHRASE_BUNCH_SIZE
except Exception as e:
print("Проблема ^^^")
print(e)
driver.quit()
parse_phrase_bunch(phrases)
def write_table_open_tag(site, region):
global RESULT_FILE
RESULT_FILE = os.path.join(get_current_dir(), PARSING_PATH_PARTICLE,
'Result/{domain}_{region}_result.html'.format(domain=site, region=region))
write_phrase_to_log("<html>\n<table>\n",
write_mode='w',
enc=WRITE_ENCODING,
full_path_to_file=RESULT_FILE)
from general.drv import get_driver, get_proxy
from general.general import get_current_dir, write_list_to_file, write_phrase_to_log, get_list
import os
import requests
from requests.exceptions import ProxyError
from random import randint
from time import sleep
from bs4 import BeautifulSoup
# Регионы https://tech.yandex.ru/xml/doc/dg/reference/regions-docpage/
USE_SLEEP_TIME = True # При реальном парсинге всегда включать. Выключить задержку только для отладки.
PARSING_PATH_PARTICLE = "../KeywordStuffing/"
INIT_PATH_PARTICLE = PARSING_PATH_PARTICLE + "Init/"
URL_AND_KEYS_FILE = os.path.join(get_current_dir(), INIT_PATH_PARTICLE, "init.csv")
READ_ENCODING = 'utf-8'
WRITE_ENCODING = 'utf-8'
SIZE_OF_CHUNK = 10
ARSENKIN = 'https://arsenkin.ru/tools/filter/'
RESULT_FILE = "" # Инициализируется в функции write_table_open_tag.
PARSE_RUSSIA = False
PARSE_MOSCOW = False
# Обязательно строкой, а не цифрой!
MOSCOW_REGION = '1' # С областью.
RUSSIA_REGION = '225'
def separate_url_and_region_and_phrases(url_phrases_list):
url = url_phrases_list[0].strip()
def get_log_path(log):
log_path = os.path.join(get_current_dir(), PARSING_PATH_PARTICLE, "log", log)
return log_path
import os
from selenium.webdriver.common.by import By
from general.drv import get_driver, USE_PROXY
from general.general import get_current_dir, get_list, clear_files, write_phrase_to_log
global_phrases = []
global_emails = []
PARSING_PATH_PARTICLE = "../CommerceParsing/"
INIT_PATH_PARTICLE = PARSING_PATH_PARTICLE + "Init/"
PHRASE_BUNCH_SIZE = 100
word_list_full_path = os.path.join(get_current_dir(), INIT_PATH_PARTICLE, "word_list.txt")
email_list_full_path = os.path.join(get_current_dir(), INIT_PATH_PARTICLE, "email_list.txt")
INDEX_LOG_FILE = "index_log.txt"
ENC = 'utf-8'
global_phrases = get_list(word_list_full_path, ENC)
global_emails = get_list(email_list_full_path, ENC)
def get_log_path(log):
log_path = os.path.join(get_current_dir(), PARSING_PATH_PARTICLE, "log", log)
return log_path
def get_phrase_counter_val():
index_log_file = get_log_path(INDEX_LOG_FILE)
try:
import os
from selenium.webdriver.common.keys import Keys
from general.general import get_current_dir, get_list, clear_files, write_list_to_file, write_phrase_to_log
from general.drv import get_driver, USE_PROXY
from time import sleep
SELECTED_REGION = 1 # https://tech.yandex.ru/xml/doc/dg/reference/regions-docpage/
PROJECT_DIR = get_current_dir()
PAGES_TO_PARSE = 3
LOGS_DIR = os.path.join(get_current_dir(), "../YandexParsing/log")
READ_ENCODING = 'utf-8'
WRITE_ENCODING = 'utf-8'
RESULT_FILE = os.path.join(LOGS_DIR, "{}_result.csv".format(SELECTED_REGION))
PARSE_RELATED_WORDS = False
def get_region():
# https://tech.yandex.ru/xml/doc/dg/reference/regions-docpage/
regions = {225: "Россия", 1: "Москва"}
return regions.get(SELECTED_REGION)
def get_phrases():
yandex_parsing_init_dir = os.path.join(
PROJECT_DIR, "../YandexParsing/init/phrases.txt")
yandex_parsing_init_file = os.path.join(yandex_parsing_init_dir)
phrases = get_list(yandex_parsing_init_file, READ_ENCODING)
return phrases
phrases = get_phrases()
from general.general import get_list, get_current_dir
from general.drv import get_driver
from general.drv import USE_PROXY
import os
from selenium.common.exceptions import NoSuchElementException
from general.drv import send_proxy_to_black_list
full_path_to_proxy_list = os.path.join(
get_current_dir(), "../CommerceParsing/Init/proxy_list.txt")
init_proxy_list = get_list(full_path_to_proxy_list)
def test_proxies():
for i in range(len(init_proxy_list)):
driver = get_driver()
driver.get("http://ip-api.com/")
element = driver.find_element_by_id("qr")
element_text = element.text
ip = element_text.split(",")
try:
region = driver.find_element_by_xpath(
'//th[text()="Country"]/following-sibling::td').text
except NoSuchElementException:
send_proxy_to_black_list(a_proxy)
driver.quit()
print("{}, {}".format(ip, region))
from itertools import product
import os
from general.general import get_current_dir, write_phrase_to_log, clear_files
import sys
import re
PATH_PARTICLE = "../SeoCombinator/"
INIT_PATH_DIR = PATH_PARTICLE + "Init/"
RESULT_PATH_DIR = os.path.join(PATH_PARTICLE, "Result")
RESULT_FILE_PATH = os.path.join(RESULT_PATH_DIR, "result.txt")
FILE_ENCODING = 'windows-1251'
INIT_DIR = os.path.join(get_current_dir(), INIT_PATH_DIR)
PLUS_WORDS = []
MINUS_WORDS = []
PHRASES = []
VARIANTS = []
WORDSTAT_LIMIT = 7 # Вордстат парсит только 7 слов.
def handle_csv_with_one_list(csv_list_from_reader):
# Файлы с общими плюс- и минус-словами содержат только одну строку.
tmp_list = csv_list_from_reader[0]
return [*filter(None, tmp_list)]
def delete_empty_values(a_list):
# Нулевой элемент в списке phrases содержит признак необходимости парсинга лесенкой.
# На всех других листах кроме листов с плюс- и минус-словами этот столбец должен присутствовать, но быть пустым.
# Поэтому нулевые элементы в списке не чистим от пустых значений.
from general.general import get_current_dir, clear_files
from general.drv import send_proxy_to_black_set
import os
from bs4 import BeautifulSoup
from general.drv import get_proxy
import requests
from requests.exceptions import ProxyError
from general.general import write_phrase_to_log
from time import sleep
LINK_COL = 1 # В какой колонке в csv-файле находится ссылка. Начинть с 0.
PARSING_PATH_PARTICLE = os.path.join(get_current_dir(), "../ParseCompetitors/")
INIT_PATH_PARTICLE = PARSING_PATH_PARTICLE + "Init/"
INIT_DIR = os.path.join(get_current_dir(), INIT_PATH_PARTICLE)
RESULT_DIR = os.path.join(PARSING_PATH_PARTICLE, "Log")
RESULT_FILE = os.path.join(RESULT_DIR, "result.csv")
READ_FILE_ENCODING = 'utf-8'
WRITE_FILE_ENCODING = 'windows-1251'
def prepare_link_list(file_list):
for f in file_list:
with open(os.path.join(INIT_DIR, f),
encoding=READ_FILE_ENCODING) as csvfile:
import csv
csv_reader = csv.reader(csvfile, delimiter=';')
csv_data = list(csv_reader)
return csv_data
