def __getUrlsInPage(url,url_xpath,next_xpath):
User_Agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"
header = {}
header["User-Agent"] = User_Agent
rq = requests.get(url, headers=header, allow_redirects=True, verify=False)
page = rq.text
page = remove_control_characters(page)
html = etree.HTML(page)
# try:
result = html.xpath(url_xpath)
try:
q = urlparse.urlparse(url).query
q = q.split('&')
if len(q) == 1:
nextpage = url + "&p=2"
else:
nextpage = int(q[1].split('=')[1]) + 1
nextpage = url.split('&')[0] + "&p=" + str(nextpage)
except Exception:
nextpage = None
#print page
#print "Next:",nextpage
return result, nextpage
def __getUrlsInPage(self, url, wantedXpath, nextUrlXpath):
User_Agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"
header = {}
header["User-Agent"] = User_Agent
rq = requests.get(url, headers=header,allow_redirects=True,verify=False)
html = rq.text
html = remove_control_characters(html)
page = etree.HTML(html)
result = page.xpath(wantedXpath)
try:
nextpage = page.xpath(nextUrlXpath)[0]
except Exception:
nextpage = None
return result, nextpage
def __getUrlsInPage(url,url_xpath,next_xpath):
page = getpagewithchrome(url,CHROME_DRIVER_PATH)
page = remove_control_characters(page)
html = etree.HTML(page)
# try:
result = html.xpath(url_xpath)
try:
nextpage = html.xpath(next_xpath)[0]
except Exception:
nextpage = None
#print page
#print "Next:",nextpage
r = []
for temp in result:
if 'ip:' in temp:
temp = temp.split('ip:')[-1]
r.append(temp)
result = r
return result, nextpage