update

crawler_sys/site_crawler/crawler_xiaohongshu.py

@@ -152,7 +152,7 @@ class Crawler_xiaohongshu():
             "accept-encoding": "gzip, deflate",
             "accept-language": "zh-CN,zh;q=0.9",
             "cache-control": "max-age=0",
-            # "cookie": "timestamp2=202101062497d4bed842476b2618e0ea;",
+            "cookie": "xhsTracker=url=user-profile&xhsshare=CopyLink; xhsTrackerId=38ec6dcb-d882-45e8-c539-834386696a14; xhsuid=Dv4OTnGbDg9LivGu; timestamp2=202101062497d4bed842476b2618e0ea; timestamp2.sig=-Jax1vd_iNZtToaWYMOMoFUmCJwojKQPnfP8iMeOpAc; extra_exp_ids=gif_clt1,ques_clt1; xhs_spses.5dde=*; xhs_spid.5dde=59a50d47116c4333.1609921946.2.1609997747.1609922354.16a344a9-3e6e-43d8-b894-33a7205e181f",
             "referer": releaserUrl,
             "sec-fetch-dest": "document",
             "sec-fetch-mode": "navigate",
@@ -175,7 +175,7 @@ class Crawler_xiaohongshu():
         # proxies = {'http': 'http://hanye:i9mmu0a3@58.55.159.141:16085/', 'https': 'http://hanye:i9mmu0a3@58.55.159.141:16085/'}
         while count <= releaser_page_num_max and count <= 1000:
             try:
-                res = retry_get_url(releaserUrl, headers=headers, proxies=proxies_num,cookies=cookie_dic)
+                res = retry_get_url(releaserUrl, headers=headers, proxies=proxies_num)
             except:
                 continue
             # print(get_page.content)