class Share():
def __init__(self, username, password):
self.launcher = Launcher(username, password)
self.driver = self.launcher.login()
self.es = Es_fb()
self.list = []
self.share_list = self.launcher.get_share_list()
def get_share(self):
self.driver.get(self.share_list[0])
for ea in self.driver.find_elements_by_xpath(
'//div[@id="repost_view_permalink"]/div/div[1]/div'):
for each in ea.find_elements_by_xpath('./div'):
author_name = each.find_element_by_xpath(
'./div/div[2]/div[1]/div[2]/div[1]/div/div/div[2]/div/div/div[2]/h5/span/span/span/a'
).text
author_id = re.findall(
re.compile('id=(\d+)'),
each.find_element_by_xpath(
'./div/div[2]/div[1]/div[2]/div[1]/div/div/div[2]/div/div/div[2]/h5/span/span/span/a'
).get_attribute('data-hovercard'))
pic_url = each.find_element_by_xpath(
'./div/div[2]/div/div[2]/div/div/a/div/img').get_attribute(
'src')
try:
content = each.find_element_by_xpath(
'./div/div[2]/div/div[2]/div[2]//p').text
except Exception as e:
content = 'None'
timestamp = int(
each.find_element_by_xpath(
'./div/div[2]/div/div[2]/div/div/div/div[2]/div/div/div[2]/div/span[3]/span/a/abbr'
).get_attribute('data-utime'))
item = {
'nick_name': author_name,
'uid': author_id,
'photo_url': pic_url,
'text': content,
'timestamp': timestamp
}
self.list.append(item)
return self.list
def save(self, indexName, typeName, list):
self.es.executeES(indexName, typeName, list)
class Share():
def __init__(self, username, password):
self.launcher = Launcher(username, password)
self.driver = self.launcher.login()
self.es = Es_fb()
self.list = []
self.share_list = self.launcher.get_share_list()
self.update_time = int(time.time())
def get_share(self):
try:
for url in self.share_list:
self.driver.get(url)
time.sleep(1)
# 退出通知弹窗进入页面
try:
self.driver.find_element_by_xpath('//div[@class="_n8 _3qx uiLayer _3qw"]').click()
except:
pass
for ea in self.driver.find_elements_by_xpath('//div[@role="feed"]/div'):
for each in ea.find_elements_by_xpath('./div'):
try:
author_name = each.find_element_by_xpath('./div[2]/div[1]/div[2]/div[1]/div/div/div[2]/div/div/div[2]/h5/span/span/span/a').text
except:
author_name = 'None'
try:
author_id = ''.join(re.findall(re.compile('id=(\d+)'),each.find_element_by_xpath('./div[2]/div[1]/div[2]/div[1]/div/div/div[2]/div/div/div[2]/h5/span/span/span/a').get_attribute('data-hovercard')))
except:
author_id = 'None'
try:
pic_url = each.find_element_by_xpath('./div[2]/div/div[2]/div/div/a/div/img').get_attribute('src')
except:
pic_url = 'None'
try:
content = each.find_element_by_xpath('./div[2]/div/div[2]/div[2]').text
except:
content = 'None'
try:
try:
timestamp = int(each.find_element_by_xpath('./div[2]/div/div[2]/div/div/div/div[2]/div/div/div[2]/div/span[3]/span/a/abbr').get_attribute('data-utime'))
except:
timestamp = int(each.find_element_by_xpath('./div[2]/div/div[2]/div/div/div/div[2]/div/div/div[2]/div/span[2]/span/a/abbr').get_attribute('data-utime'))
except:
timestamp = 'None'
try:
mid = ''.join(re.findall(re.compile('/(\d+)'),each.find_element_by_xpath('./div[2]/div/div[2]/div/div/div/div[2]/div/div/div[2]/div/span[3]/span/a').get_attribute('href')))
except:
mid = 'None'
try:
root_mid = ''.join(re.findall(re.compile('story_fbid=(\d+)'),each.find_element_by_xpath('./div[2]/div/div[2]/div/div/div/div[2]/div/div/div[2]/h5/span/span/a').get_attribute('href')))
except:
root_mid = 'None'
item = {'uid':author_id, 'photo_url':pic_url, 'nick_name':author_name, 'mid':mid, 'timestamp':timestamp,\
'text':content, 'update_time':self.update_time, 'root_text':content, 'root_mid':root_mid}
self.list.append(item)
finally:
self.driver.close()
return self.list
def save(self, indexName, typeName, list):
self.es.executeES(indexName, typeName, list)
author_id = re.findall(
re.compile('id=(\d+)'),
each.find_element_by_xpath(
'./div/div[2]/div[1]/div[2]/div[1]/div/div/div[2]/div/div/div[2]/h5/span/span/span/a'
).get_attribute('data-hovercard'))
pic_url = each.find_element_by_xpath(
'./div/div[2]/div/div[2]/div/div/a/div/img').get_attribute(
'src')
try:
content = each.find_element_by_xpath(
'./div/div[2]/div/div[2]/div[2]//p').text
except Exception as e:
content = 'None'
time = each.find_element_by_xpath(
'./div/div[2]/div/div[2]/div/div/div/div[2]/div/div/div[2]/div/span[3]/span/a/abbr'
).get_attribute('data-utime')
root_url = 'https://www.facebook.com/' + each.find_element_by_xpath(
'./div/div[2]/div/div[2]/div/div/div/div[2]/div/div/div[2]/h5/span/span/a'
).get_attribute('href')
def save(self, indexName, typeName, item):
es.executeES(indexName, typeName, item)
if __name__ == '__main__':
fb = Launcher('18538728360', 'zyxing,0513')
es = es_twitter()
share_list = fb.get_share_list()
share = Share()
share.get_share()
class Share():
def __init__(self, username, password):
self.launcher = Launcher(username, password)
self.es = Es_fb()
self.list = []
self.share_list, self.driver = self.launcher.get_share_list()
self.update_time = int(time.time())
def get_share(self):
for url in self.share_list:
self.driver.get(url)
time.sleep(120)
# 退出通知弹窗进入页面
try:
self.driver.find_element_by_xpath(
'//div[@class="_n8 _3qx uiLayer _3qw"]').click()
except:
pass
page = self.driver.page_source
self.driver.save_screenshot('get_share000.png')
#for ea in self.driver.find_elements_by_xpath('//div[@role="feed"]/div'):
#for ea in divs:
# for each in ea.find_elements_by_xpath('./div'):
try:
author_name = self.driver.find_element_by_xpath(
'//table[@role="presentation"]/tbody/tr/td[2]/div/h3/strong/a'
).text
except:
author_name = ''
print author_name
try:
author_id = ''.join(
re.search(re.compile('id%3D(\d+)&'), url).group(1))
except:
author_id = ''
print author_id
# try:
# pic_url = each.find_element_by_xpath('./div[2]/div/div[2]/div/div/a/div/img').get_attribute('src')
# except:
# pic_url = 'None'
try:
content = self.driver.find_element_by_xpath(
'/html/body/div/div/div[2]/div/div[1]/div[1]/div/div[1]/div[2]'
).text
except:
content = ''
try:
timestamp = int(
re.search(
re.compile('"publish_time":(\d+),'),
page.replace(' ',
'').replace('\n',
'').replace('\t',
'')).group(1))
except:
timestamp = ''
print timestamp
try:
mid = ''.join(
re.search(re.compile('fbid%3D(\d+)%'), url).group(1))
except:
mid = ''
print mid
try:
root_mid = ''.join(
re.search(
re.compile(
'"original_content_id":"(\d+)"'
), page).group(1))
except:
root_mid = ''
print root_mid
try:
root_text = self.driver.find_element_by_xpath(
'/html/body/div/div/div[2]/div/div[1]/div[1]/div/div[1]/div[3]/div[2]/div/div/div[2]'
).text.replace(' ', '').replace('\n', '').replace('\t', '')
except:
root_text = ''
print root_text
item = {'uid':author_id, 'nick_name':author_name, 'mid':mid, 'timestamp':timestamp,\
'text':content, 'update_time':self.update_time, 'root_text':root_text, 'root_mid':root_mid}
self.list.append(item)
self.driver.quit()
return self.list
def save(self, indexName, typeName, list):
self.es.executeES(indexName, typeName, list)
