def collect(self):
LoginController.login_by_cookie(self.browser)
#self.browser.get('http://weibo.com/5579712614/follow')
#time.sleep(4)
a = self.browser.find_element_by_xpath("//a[@node-type='mUpload']")
a.send_keys(open('2.jpg'))
list = FocusFollowPage.focus_list_all_with_func(self.browser, self.p)
print('')
def collect(self):
LoginController.login_by_cookie(self.browser)
#self.browser.get('http://weibo.com/5579712614/follow')
#time.sleep(4)
a = self.browser.find_element_by_xpath("//a[@node-type='mUpload']")
a.send_keys(open('2.jpg'))
list = FocusFollowPage.focus_list_all_with_func(self.browser, self.p)
print('')
def __send(self, text, url):
passwd_dict = PasswdUtil.get_passwd_dict()
browser = LoginController.get_browser()
try:
service.send_weibo(text, url, LoginController.mobile_login(browser, passwd_dict[Const.WEIBO_USERNAME], passwd_dict[Const.WEIBO_PASSWD]))
except Exception as e:
print e
browser.quit()
def search():
date = DateUtil.time_to_str(DateUtil.substract_day(DateUtil.now(), 1), Const.STYLE_YYMMDD)
txt = "又到了推荐极具视觉冲击图片的时刻了[微笑][微笑] @当幸福敲不开门 "
url = "http://freepic.wetu.me/preview/%s%s.jpg"
browser = LoginController.get_browser()
passwd_dict = PasswdUtil.get_passwd_dict()
LoginController.mobile_login(browser, passwd_dict[Const.WEIBO_USERNAME], passwd_dict[Const.WEIBO_PASSWD])
service.send_weibo_pics(txt, [url % (date, "i"), url % (date, "p")], browser)
def publish_articles():
url = 'http://www.jianshu.com'
html = BeautifulSoup(HttpUtil.request(url))
articles_soup = [ parse_article_soup(article) for article in html.find(attrs={"class": "article-list thumbnails"}).findAll('li')]
sorted_articles = sorted(articles_soup, key=lambda articl_soup:articl_soup[0], reverse=True)
article_body = service.jian_shu_article_retrive(url + sorted_articles[0][1])
browser = LoginController.get_browser()
passwd_dict = PasswdUtil.get_passwd_dict()
send_text = '《%s》 又到每天推荐文章的时候到了，这些都是精选的枕边读物哦，希望大家喜欢@当幸福敲不开门[害羞][害羞][害羞] ' % article_body[0]
service.send_weibo(send_text, service.txt_to_pic(article_body[1], browser), LoginController.mobile_login(browser, passwd_dict[Const.WEIBO_USERNAME], passwd_dict[Const.WEIBO_PASSWD]))
def search():
date = DateUtil.time_to_str(DateUtil.substract_day(DateUtil.now(), 1),
Const.STYLE_YYMMDD)
txt = '又到了推荐极具视觉冲击图片的时刻了[微笑][微笑] @当幸福敲不开门 '
url = 'http://freepic.wetu.me/preview/%s%s.jpg'
browser = LoginController.get_browser()
passwd_dict = PasswdUtil.get_passwd_dict()
LoginController.mobile_login(browser, passwd_dict[Const.WEIBO_USERNAME],
passwd_dict[Const.WEIBO_PASSWD])
service.send_weibo_pics(txt, [url % (date, 'i'), url % (date, 'p')],
browser)
def __send(self, text, url):
passwd_dict = PasswdUtil.get_passwd_dict()
browser = LoginController.get_browser()
try:
service.send_weibo(
text, url,
LoginController.mobile_login(browser,
passwd_dict[Const.WEIBO_USERNAME],
passwd_dict[Const.WEIBO_PASSWD]))
except Exception as e:
print e
browser.quit()
def search(self):
driver = LoginController.get_firfox()
LoginController.login(driver, self.name, self.passwd)
driver.get('http://weibo.com/messages?topnav=1&wvr=6')
list = MsgPage.get_other_fans_list(driver)
list[0].click()
list = MsgPage.get_other_fans_list(driver)
for friend in list:
friend.click()
MsgPage.send_fans_msg(driver, u'hello')
time.sleep(1)
driver.get('http://weibo.com/duzijian?is_hot=1')
weibo_list = [ WeiboPageCommon.weibo_parse(weibo) for weibo in WeiboPageCommon.get_all_weibo(driver)]
print ''
def publish_articles():
url = 'http://www.jianshu.com'
html = BeautifulSoup(HttpUtil.request(url))
articles_soup = [
parse_article_soup(article)
for article in html.find(attrs={
"class": "article-list thumbnails"
}).findAll('li')
]
sorted_articles = sorted(articles_soup,
key=lambda articl_soup: articl_soup[0],
reverse=True)
article_body = service.jian_shu_article_retrive(url +
sorted_articles[0][1])
browser = LoginController.get_browser()
passwd_dict = PasswdUtil.get_passwd_dict()
send_text = '《%s》 又到每天推荐文章的时候到了，这些都是精选的枕边读物哦，希望大家喜欢@当幸福敲不开门[害羞][害羞][害羞] ' % article_body[
0]
service.send_weibo(
send_text, service.txt_to_pic(article_body[1], browser),
LoginController.mobile_login(browser,
passwd_dict[Const.WEIBO_USERNAME],
passwd_dict[Const.WEIBO_PASSWD]))
def publish(self):
self.browser.set_page_load_timeout(120)
passwd_dict = PasswdUtil.get_passwd_dict()
LoginController.mobile_login(self.browser, passwd_dict[Const.WEIBO_USERNAME], passwd_dict[Const.WEIBO_PASSWD])
#LoginController.login_by_cookie(self.browser)
print('等待4s,滚动屏幕')
WeiboPageCommon.scroll(self.browser)
time.sleep(4)
WeiboPageCommon.scroll(self.browser)
time.sleep(4)
WeiboPageCommon.scroll(self.browser)
time.sleep(4)
print('等待结束')
try:
weibo_list = WeiboPageCommon.get_all_weibo(self.browser)
except:
traceback.print_exc()
self.browser.get('http://weibo.com/')
time.sleep(4)
weibo_list = WeiboPageCommon.get_all_weibo(self.browser)
print('需要解析的微博数目:' + str(len(weibo_list)))
weibos = map(lambda weibo_driver:self.__get_webibo_info(weibo_driver), weibo_list)
#weibos.extend(map(lambda weibo_driver:self.__get_webibo_info(weibo_driver), WeiboPageCommon.get_all_weibo(self.browser)[len(weibo_list):]))
weibos = filter(lambda w : w is not None , weibos)
#打开新的选项卡
#self.browser.find_element_by_tag_name("body").send_keys(Keys.CONTROL + 't')
#self.browser.execute_script("window.open('http://weibo.com/','_blank');")
#wins = self.browser.window_handles
#self.browser.switch_to_window(wins[1])
#self.browser.set_window_size(1366, 768)
map(lambda weibo:self.__get_weiboer_info(weibo), weibos)
#self.browser.switch_to_window(wins[0])
sorted_weibos = PublishStrategy.nums_strategy(weibos)
WeiboPageCommon.forword_by_comment(self.browser, sorted_weibos[0])
self.browser.close()
self.browser.quit()
print ''
weibo = WeiboPageCommon.weibo_and_comment_parse(weibo_driver)
#weibo.author_info = author_info
except :
traceback.print_exc()
return None
return weibo
#获取微博用户信息
def __get_weiboer_info(self, weibo):
try:
print('访问:'),
print(weibo.author_url)
self.browser.get(weibo.author_url)
time.sleep(4)
info = FriendHomePage.get_friend_info(self.browser)
fans_info = FansInfo()
fans_info.focus_num = info[0]
fans_info.fans_num = info[1]
fans_info.weibo_num = info[2]
weibo.author_info = fans_info
pass
except Exception as e:
pass
if __name__ == '__main__':
crawler = WeiboPublishCrawler(LoginController.get_browser())
try:
crawler.publish()
except:
crawler.browser.quit()
soup = BeautifulSoup(html)
data = {"reserve_check": 1, "text": "", "html": soup.find('body')}
url = 'http://www.changweibo.com/convert_changweibo_com.php'
response = HttpUtil.request_post(url, data)
img_url = json.loads(response)['image_url']
print(img_url)
return img_url
#返回简书文章内容和标题
def jian_shu_article_retrive(url):
html = HttpUtil.request(url)
content_soup = BeautifulSoup(
html, fromEncoding="utf-8").find(attrs={"class": "article"})
title = content_soup.find(attrs={"class": "title"}).text.encode('utf-8')
content = content_soup.find(attrs={"class": "show-content"})
return (title, content)
if __name__ == '__main__':
article = jian_shu_article_retrive('http://www.jianshu.com/p/6b36ae903883')
browser = LoginController.get_browser()
passwd_dict = PasswdUtil.get_passwd_dict()
send_weibo(
article[0], txt_to_pic(article[1], browser),
LoginController.mobile_login(browser,
passwd_dict[Const.WEIBO_USERNAME],
passwd_dict[Const.WEIBO_PASSWD]))
#print txt_to_pic([1], LoginController.get_chrome())
#print(jian_shu_article_retrive('http://www.jianshu.com/p/f3237b61d54a'))
#coding:utf-8
import sys
import time
sys.path.append('/home/workspace/webcrawler/weiboCrawler')
from loginController import LoginController
from Pages import FocusFollowPage
class FansInfoCollector:
def __init__(self, browser):
self.browser = browser
def collect(self):
LoginController.login_by_cookie(self.browser)
#self.browser.get('http://weibo.com/5579712614/follow')
#time.sleep(4)
a = self.browser.find_element_by_xpath("//a[@node-type='mUpload']")
a.send_keys(open('2.jpg'))
list = FocusFollowPage.focus_list_all_with_func(self.browser, self.p)
print('')
def p(self, fans):
print fans.name
if __name__ == '__main__':
crawler = FansInfoCollector(LoginController.get_chrome())
crawler.collect()
#coding:utf-8
import sys
import time
sys.path.append('/home/workspace/webcrawler/weiboCrawler')
from loginController import LoginController
from Pages import FocusFollowPage
class FansInfoCollector:
def __init__(self, browser):
self.browser = browser
def collect(self):
LoginController.login_by_cookie(self.browser)
#self.browser.get('http://weibo.com/5579712614/follow')
#time.sleep(4)
a = self.browser.find_element_by_xpath("//a[@node-type='mUpload']")
a.send_keys(open('2.jpg'))
list = FocusFollowPage.focus_list_all_with_func(self.browser, self.p)
print('')
def p(self, fans):
print fans.name
if __name__ == '__main__':
crawler = FansInfoCollector(LoginController.get_chrome())
crawler.collect()
soup = BeautifulSoup(html)
data={
"reserve_check":1,
"text":"",
"html":soup.find('body')
}
url = 'http://www.changweibo.com/convert_changweibo_com.php'
response = HttpUtil.request_post(url, data)
img_url = json.loads(response)['image_url']
print(img_url)
return img_url
#返回简书文章内容和标题
def jian_shu_article_retrive(url):
html = HttpUtil.request(url)
content_soup = BeautifulSoup(html, fromEncoding="utf-8").find(attrs={"class": "article"})
title = content_soup.find(attrs={"class": "title"}).text.encode('utf-8')
content = content_soup.find(attrs={"class": "show-content"})
return (title, content)
if __name__ == '__main__':
article = jian_shu_article_retrive('http://www.jianshu.com/p/6b36ae903883')
browser = LoginController.get_browser()
passwd_dict = PasswdUtil.get_passwd_dict()
send_weibo(article[0], txt_to_pic(article[1], browser), LoginController.mobile_login(browser, passwd_dict[Const.WEIBO_USERNAME], passwd_dict[Const.WEIBO_PASSWD]))
#print txt_to_pic([1], LoginController.get_chrome())
#print(jian_shu_article_retrive('http://www.jianshu.com/p/f3237b61d54a'))
