本文整理匯總了Python中Crawler.Crawler.get_page方法的典型用法代碼示例。如果您正苦於以下問題：Python Crawler.get_page方法的具體用法？Python Crawler.get_page怎麽用？Python Crawler.get_page使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類Crawler.Crawler的用法示例。
在下文中一共展示了Crawler.get_page方法的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: get_article
# 需要導入模塊: from Crawler import Crawler [as 別名]
# 或者: from Crawler.Crawler import get_page [as 別名]
def get_article(self, url):
crawler = Crawler()
# get html data from url
web_data = crawler.get_page(url)
soup = BeautifulSoup(web_data, 'html.parser')
# remove link news
[e.extract() for e in soup('div', {'class':'link_news'})]
# article title
self.title = soup('h3', {'id':'articleTitle'})[0].text
# create date and time of article
date_time = soup('span', {'class':'t11'})[0].text.split()
self.date = date_time[0]
self.time = date_time[1]
# press name
press_logo = soup('div', {'class':'press_logo'})[0]
self.press = press_logo.find('img')['alt']
del press_logo
# article contents
self.contents = soup('div', {'id':'articleBodyContents'})[0].text
self.contents = re.sub('[\n\r]', '', self.contents)示例2: get_list
# 需要導入模塊: from Crawler import Crawler [as 別名]
# 或者: from Crawler.Crawler import get_page [as 別名]
def get_list(section, date):
# NAVER news url
naver_news_url = 'http://news.naver.com/main/list.nhn'
naver_news_parameter = {'mode':'LSD', 'mid':'sec', 'sid1':'', 'date':date, 'page':''}
naver_news_parameter['sid1'] = section
page = 1
url_list = []
while True:
naver_news_parameter['page'] = page
url = naver_news_url + '?' + urllib.urlencode(naver_news_parameter)
# get html data
crawler = Crawler()
web_data = crawler.get_page(url)
# html parsing
soup= BeautifulSoup(web_data, 'html.parser')
list_body = soup('div', {'class':'list_body newsflash_body'})[0]
# get each article's url
list_body = list_body.findAll('li')
current_list = []
for e in list_body:
current_list.append(e.find('a')['href'])
del list_body
# break when current page is end of url list
if current_list[0] in url_list:
break
# add to url list
url_list += current_list
# next url page
page += 1
return url_list