def add_to_result(block, title, year, month, day, driver, keyword_list):
if share.double_check(keyword_list, title) and share.compare_date(
year, month, day) and not check_exist(title):
b = block.find_element_by_class_name('article-wrapper')
link = b.find_element_by_tag_name('a').get_attribute('href')
# body = find_body(link,driver)
result_list.append(share.Page_info(link, title, None))
return
def list_article(block, keyword_list, driver):
title = block.find_element_by_tag_name('h2').text
date = block.find_element_by_tag_name('time').text.split('.')
y, m, d = date[2], date[0], date[1]
# print(title,date)
if share.double_check(keyword_list, title) and share.compare_date(
y, m, d) and not check_exist(title):
link = block.find_element_by_tag_name('a').get_attribute('href')
# body = find_body(link,driver)
result_list.append(share.Page_info(link, title, None))
def feature_box(sublist, keyword_list, driver, count):
title = sublist[2]
if share.double_check(keyword_list, title):
if count == 1:
xpath = '//*[@id="content"]/div/div[1]/div[2]/div[2]/div/article[1]/div[3]/h2/a'
elif count == 2:
xpath = '//*[@id="content"]/div/div[1]/div[2]/div[2]/div/article[2]/div[3]/h2/a'
link_element = driver.find_element_by_xpath(xpath)
link = link_element.get_attribute("href")
# body = find_body(link,driver)
result_list.append(share.Page_info(link, title, None))
def featured_head(sublist, keyword_list, driver):
title = sublist[3]
if share.double_check(keyword_list, title):
link_element = driver.find_element_by_xpath(
'//*[@id="content"]/div/div[1]/div[2]/div[1]/article/div/div/h1/a')
link = link_element.get_attribute("href")
driver.get(link)
body_element = driver.find_element_by_xpath(
'//*[@id="content"]/div/div[1]/article/div/div[1]/p[1]')
body = body_element.text.strip()
driver.back()
result_list.append(share.Page_info(link, title, body))
def same_h(block, keyword_list, driver):
title = block.find_element_by_tag_name('h2').text
date = block.find_element_by_tag_name('time').text
if len(date.split('.')) == 1:
date = date.split()
y, m, d = date[2], date[0], date[1][:-1]
else:
date = date.split('.')
y, m, d = date[2], date[0], date[1]
if share.double_check(keyword_list, title) and share.compare_date(
y, m, d) and not check_exist(title):
b = block.find_element_by_tag_name('h2')
link = b.find_element_by_tag_name('a').get_attribute('href')
# body = find_body(link,driver)
result_list.append(share.Page_info(link, title, None))
def squared_label(block, keyword_list, driver):
text_list = [
text.strip() for text in block.text.split('\n') if text.strip() != ''
]
title = text_list[1]
date = text_list[-1].split('|')[-1].strip().split()
y, m, d = date[2], date[0], date[1][:-1]
if share.double_check(keyword_list, title) and share.compare_date(
y, m, d) and not check_exist(title):
b = block.find_element_by_class_name('article-wrapper')
link = b.find_element_by_tag_name('a').get_attribute('href')
xpath = '//*[@id="wrapper"]/div[1]/div/div/section/div[2]/div/p'
driver.get(link)
para = driver.find_element_by_xpath(xpath)
body = para.text
result_list.append(share.Page_info(link, title, body))
driver.back()
def main(keyword_list: list):
print('Searching Cleantechnica......')
result_list = []
try:
for l in link_list:
driver = webdriver.Chrome(share.FILE_PATH + '/chromedriver')
# print(l)
driver.get(l)
time.sleep(.1)
driver.refresh()
main_part = driver.find_elements_by_class_name('omc-blog-one')
for article in main_part:
date = article.find_element_by_class_name(
'omc-date-time-one').text.split('|')[0][13:-1].split()
y, m, d = date[-1], date[0], date[1][:-3]
title = article.find_element_by_tag_name('h2').text
link = article.find_elements_by_tag_name('a')[1].get_attribute(
'href')
if share.double_check(keyword_list,
title) and share.compare_date(y, m, d):
result_list.append(share.Page_info(link, title, None))
driver.close()
driver = webdriver.Chrome(share.FILE_PATH + '/chromedriver')
for page in result_list:
driver.get(page.link)
time.sleep(1)
page.body = driver.find_element_by_xpath(
'//*[@id="omc-full-article"]/p[2]').text
if len(page.body) <= 40:
page.body = driver.find_element_by_xpath(
'//*[@id="omc-full-article"]/p[3]').text
if len(page.body) <= 40:
page.body = driver.find_element_by_xpath(
'//*[@id="omc-full-article"]/p[4]').text
if len(result_list) != 0:
share.write_file(result_list)
print('Finished')
finally:
try:
driver.close()
except selenium.common.exceptions.WebDriverException:
pass
def main(keyword_list: str):
print("Searching CleanTech......")
driver = webdriver.Chrome(share.FILE_PATH + '/chromedriver')
try:
driver.get("https://www.cleantech.com/category/cleantech-news/")
main_xpath = '//*[@id="main"]/section[2]/div'
blocks = driver.find_elements_by_tag_name("article")
for article in blocks:
whole_text = article.text.rstrip().lstrip()
sentence_list = whole_text.split('\n')
copy_list = list(sentence_list)
for item in sentence_list:
strip = item.rstrip().lstrip()
if strip == '':
copy_list.remove(item)
final_list = [sentence.rstrip().lstrip() for sentence in copy_list]
title = final_list[0].encode('utf8').decode('utf-8', 'strict')
date = final_list[1][10:]
if process(date):
if share.double_check(keyword_list, title):
description = final_list[2]
post_id = article.get_attribute('id')
xpath = generate_xpath(post_id)
link_element = driver.find_element_by_xpath(xpath)
link = link_element.get_attribute('href')
result_list.append(
share.Page_info(link, title, description))
else:
continue
else:
continue
if len(result_list) != 0:
share.write_file(result_list)
print("Finished")
finally:
driver.close()
def main(keyword_list: list):
print("Searching Azocleantech......")
driver = webdriver.Chrome(share.FILE_PATH + '/chromedriver')
driver.get('https://www.azocleantech.com/news-index.aspx')
try:
main_part = driver.find_element_by_xpath(
'//*[@id="ctl00_cphBody_latestNewsItems_posts"]')
full_list = main_part.find_elements_by_class_name('row')
striped = [a.text.strip() for a in full_list]
length = int(len(striped) / 2)
for i in range(length):
title_and_despt = striped[2 * i].split('\n')
title = title_and_despt[0].strip()
date = striped[2 * i + 1].split('\n')[-1].strip().split()
y, m, d = date[2], date[1], date[0]
if share.compare_date(y, m, d) and share.double_check(
keyword_list, title):
link, body = get_link(i, driver)
result_list.append(share.Page_info(link, title, body))
if len(result_list) != 0:
share.write_file(result_list)
print("Finished")
finally:
driver.close()
def main(keyword_list):
print("Searching NengApp......")
driver = webdriver.Chrome(share.FILE_PATH + '/chromedriver')
index = 0
finish = False
try:
while True:
url = generate_url(index)
driver.get(url)
article_list = driver.find_elements_by_class_name('news-item')
for article in article_list:
info = article.find_element_by_class_name('news-info')
if compare_date(info.text) == False:
finish = True
break
content = article.find_element_by_class_name('news-content')
title = content.find_element_by_tag_name('a').text
if share.double_check(keyword_list,
title) and not check_exist(title):
link = article.find_element_by_tag_name('a').get_attribute(
'href')
result_list.append(share.Page_info(link, title, None))
if finish:
break
index += 1
for page in result_list:
driver.get(page.link)
paragraphs = driver.find_elements_by_tag_name('p')
for p in paragraphs:
if len(p.text) >= 15:
page.body = p.text
break
share.write_file(result_list)
print('Finished')
finally:
driver.close()
def test_add(block, title, year, month, day, driver):
b = block.find_element_by_class_name('article-wrapper')
link = b.find_element_by_tag_name('a').get_attribute('href')
body = find_body(link, driver)
print(share.Page_info(link, title, body))
def process_articles(art_list: list, keyword_list: list) -> None:
for article in art_list:
title = article.find_element_by_class_name('article-item-title').text
if share.double_check(keyword_list, title):
link = article.find_element_by_tag_name('a').get_attribute('href')
result_list.append(share.Page_info(link, title, None))