def view(keyword, driver_path):
#for ubuntu
display = Display(visible=1, size=(1920, 1080))
display.start()
#chrome_options = webdriver.ChromeOptions()
#chrome_options.add_argument('headless')
#chrome_options.add_argument('--disable-gpu')
#chrome_options.add_argument('lang=ko_KR')
#driver = webdriver.Chrome(str(driver_path), chrome_options=chrome_options) # 드라이버 설정
driver = webdriver.Chrome(driver_path) # 드라이버 설정
keyword = '{}'.format(keyword)
driver.get(
"https://search.naver.com/search.naver?where=view&sm=tab_jum&query={}&qvt=0"
.format(keyword)) # 키워드 검색
driver.implicitly_wait(time_to_wait=0.3)
while True:
last = driver.find_element_by_xpath('//*[@id="footer"]')
action = ActionChains(driver)
action.move_to_element(last).perform()
driver.implicitly_wait(time_to_wait=0.3)
height = driver.execute_script("return document.body.scrollHeight")
print(height)
time.sleep(0.5)
if len(
driver.find_elements_by_xpath(
'//*[@class="review_loading _trigger_base"]')) == 0:
print("Scroll Finished, Please Check.")
break
li = driver.find_element_by_xpath('//ul[@Class="lst_total _list_base"]')
html = li.get_attribute('innerHTML')
soup = bs(html, 'html.parser')
Urls = [
k.attrs['href']
for k in soup.find_all(attrs={'class': 'api_txt_lines total_tit'})
]
title = [
k.get_text()
for k in soup.find_all(attrs={'class': 'api_txt_lines total_tit'})
]
rank = [
li_.get_attribute('data-cr-rank')
for li_ in li.find_elements_by_xpath('//li[@class="bx _svp_item"]')
]
date = [
k.get_text()
for k in soup.find_all(attrs={'class': 'sub_time sub_txt'})
]
print(len(Urls), len(rank), len(title), len(date))
driver.close()
#for ubuntu
display.quit()
return Urls, rank, title, date
class MailcrawlSpider(scrapy.Spider):
name = 'mailcrawl'
allowed_domains = ['industrie-expo.com']
#start_urls = ['http://www.industrie-expo.com/liste-catalogue-exposants/']
def start_requests(self):
self.setUp()
self.driver.get(
"http://www.industrie-expo.com/liste-catalogue-exposants/")
pageid = 2
while True:
try:
driver.execute_script("searchExposant(" + str(pageid) +
", '#')")
pageid += 1
print(pageid)
except:
break
self.tearDown()
#for url in urls:
# yield scrapy.Request(url=url, callback=self.parse)
def parse(self, response):
pass
def setUp(self):
self.display = Display(visible=0, size=[800, 600])
self.display.start()
self.driver = webdriver.Firefox()
def tearDown(self):
self.driver.close()
self.display.quit()
for tag2 in supers1.find_all('span',attrs={'style': 'color: #ff0000'}):
m_context2 = tag2.find('p').get_text()
#print(m_context2)
dict['tag'] = m_context2.replace('类别:','')
#break
st1 = dict['url']+','+dict['name']+','+dict['author']+','+dict['tag']+','+str(dict['num'])+','+dict['format']+','+dict['iframeid']+'\n'
storestr(st1)
lst.append(dict['name'])
store(lst)
print(lst)
return dict
if __name__=="__main__":
display = Display(visible=0, size=(900, 800))
display.start()
driver = webdriver.Firefox(executable_path='./geckodriver')
lst = load()
url = "https://www.5tps.com/mlist/46_1.html" #请求要访问小说页面的主页面
for i in range(2, 65):
url = "https://www.5tps.com/mlist/46_%d.html"%i
dict1=response = dump_load(lst,driver,url) # 获取小说每页列表并解析出 音频地址 和 小说单张名称
#st1 = dict1['url']+','+dict1['name']+','+dict1['author']+','+dict1['tag']+','+str(dict1['num'])+','+dict1['format']
#print(st1)
#lst.append(dict1)
#storestr(st1)
#print(lst)
driver.quit()
display.quit()
