python爬虫动态数据获取失败_知乎动态数据加载爬虫

base_url = https://www.zhihu.com/api/v4/topics/21239580/feeds/essence?

#数据包的头部信息完整不容易被反爬

headers = {

referer: https://www.zhihu.com/topic/21239580/top-answers,

User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36,

X-Requested-With: fetch,

}

#获取动态加载的json文件

def get_page(offset):

params = {

include:data[?(target.type=topic_sticky_module)].target.data[?(target.type=answer)].target.content,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp;data[?(target.type=topic_sticky_module)].target.data[?(target.type=answer)].target.is_normal,comment_count,voteup_count,content,relevant_info,excerpt.author.badge[?(type=best_answerer)].topics;data[?(target.type=topic_sticky_module)].target.data[?(target.type=article)].target.content,voteup_count,comment_count,voting,author.badge[?(type=best_answerer)].topics;data[?(target.type=topic_sticky_module)].target.data[?(target.type=people)].target.answer_count,articles_count,gender,follower_count,is_followed,is_following,badge[?(type=best_answerer)].topics;data[?(target.type=answer)].target.annotation_detail,content,hermes_label,is_labeled,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp;data[?(target.type=answer)].target.author.badge[?(type=best_answerer)].topics;data[?(target.type=article)].target.annotation_detail,content,hermes_label,is_labeled,author.badge[?(type=best_answerer)].topics;data[?(target.type=question)].target.annotation_detail,comment_count;,

limit: 10,

offset: offset #offset是一个变量

}

url = base_url + urlencode(params)

try:

response = requests.get(url, headers=headers)

if response.status_code == 200:

return response.json()

except requests.ConnectionError as e:

print(Error, e.args)

base_url = https://www.zhihu.com/api/v4/topics/21239580/feeds/essence? #数据包的头部信息完整不容易被反爬 headers = { referer: https://www.zhihu.com/topic/21239580/top-answers, User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36, X-Requested-With: fetch, } #获取动态加载的json文件 def get_page(offset): params = { include:data[?(target.type=topic_sticky_module)].target.data[?(target.type=answer)].target.content,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp;data[?(target.type=topic_sticky_module)].target.data[?(target.type=answer)].target.is_normal,comment_count,voteup_count,content,relevant_info,excerpt.author.badge[?(type=best_answerer)].topics;data[?(target.type=topic_sticky_module)].target.data[?(target.type=article)].target.content,voteup_count,comment_count,voting,author.badge[?(type=best_answerer)].topics;data[?(target.type=topic_sticky_module)].target.data[?(target.type=people)].target.answer_count,articles_count,gender,follower_count,is_followed,is_following,badge[?(type=best_answerer)].topics;data[?(target.type=answer)].target.annotation_detail,content,hermes_label,is_labeled,relationship.is_authorized,is_author,voting,is_thanked,is_nothelp;data[?(target.type=answer)].target.author.badge[?(type=best_answerer)].topics;data[?(target.type=article)].target.annotation_detail,content,hermes_label,is_labeled,author.badge[?(type=best_answerer)].topics;data[?(target.type=question)].target.annotation_detail,comment_count;, limit: 10, offset: offset #offset是一个变量 } url = base_url + urlencode(params) try: response = requests.get(url, headers=headers) if response.status_code == 200: return response.json() except requests.ConnectionError as e: print(Error, e.args)