Commit cbf1f77e authored by litaolemo's avatar litaolemo

update

parent 30f71164
......@@ -65,8 +65,10 @@ class Crawler_xiaohongshu():
self.video_data['platform'] = self.platform
self.chrome_options = webdriver.ChromeOptions()
# self.chrome_options.add_argument('--headless')
# self.chrome_options.add_argument('--disable-gpu')
# self.chrome_options.add_argument("--no-sandbox")
self.chrome_options.add_argument('--disable-gpu')
self.chrome_options.add_argument("--no-sandbox")
self.chrome_options.add_argument( '--proxy-server=http://{ip}:{port}'.format(ip='171.80.186.177',
port=15455))
self.chrome_options.add_argument('User-Agent="Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1"')
self.chrome_options.add_argument('accept="text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9"')
self.chrome_options.add_argument('accept-encoding="gzip, deflate"')
......@@ -82,7 +84,7 @@ class Crawler_xiaohongshu():
self.timestamp = str(datetime.datetime.now().timestamp() * 1e3)
prefs = {"profile.managed_default_content_settings.images": 2}
self.chrome_options.add_experimental_option("prefs", prefs)
# self.driver = webdriver.Chrome(options=self.chrome_options)
self.driver = webdriver.Chrome(options=self.chrome_options)
def __exit__(self):
self.driver.close()
......@@ -137,24 +139,24 @@ class Crawler_xiaohongshu():
doc_type=None,
output_to_es_register=False,
push_to_redis=False, proxies_num=None, **kwargs):
# self.driver.get("https://www.xiaohongshu.com/")
# self.driver.implicitly_wait(2)
# time.sleep(1)
# self.driver.get(releaserUrl)
# self.driver.implicitly_wait(2)
# time.sleep(1)
#
#
# self.driver.refresh()
# page_element = self.driver.find_element_by_xpath("//*").get_attribute("outerHTML")
# print(page_element)
# cookie = self.driver.get_cookies()
self.driver.get("https://www.xiaohongshu.com/")
self.driver.implicitly_wait(2)
time.sleep(1)
self.driver.get(releaserUrl)
self.driver.implicitly_wait(2)
time.sleep(1)
# self.driver.refresh()
page_element = self.driver.find_element_by_xpath("//*").get_attribute("outerHTML")
print(page_element)
cookie = self.driver.get_cookies()
#
# print(self.driver.get_log("performance"))
# cookie_dic={}
# for k in cookie:
# cookie_dic[k["name"]] = k["value"]
# print(cookie_dic)
cookie_dic={}
for k in cookie:
cookie_dic[k["name"]] = k["value"]
print(cookie_dic)
headers = {
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"accept-encoding": "gzip, deflate",
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment