python实现知乎高颜值图片爬取
导入相关包
importtime importpydash importbase64 importrequests fromlxmlimportetree fromaipimportAipFace frompathlibimportPath
百度云人脸检测申请信息
#唯一必须填的信息就这三行 APP_ID="xxxxxxxx" API_KEY="xxxxxxxxxxxxxxxx" SECRET_KEY="xxxxxxxxxxxxxxxx" #过滤颜值阈值，存储空间大的请随意 BEAUTY_THRESHOLD=55 AUTHORIZATION="oauthc3cef7c66a1843f8b3a9e6a1e3160e20" #如果权限错误，浏览器中打开知乎，在开发者工具复制一个，无需登录 #建议最好换一个，因为不知道知乎的反爬虫策略，如果太多人用同一个，可能会影响程序运行
以下皆无需改动
#每次请求知乎的讨论列表长度，不建议设定太长，注意节操 LIMIT=5 #这是话题『美女』的ID，其是『颜值』（20013528）的父话题 SOURCE="19552207"
爬虫假装下正常浏览器请求
USER_AGENT="Mozilla/5.0(WindowsNT5.1)AppleWebKit/534.55.3(KHTML,likeGecko)Version/5.1.5Safari/534.55.3"
REFERER="https://www.zhihu.com/topic/%s/newest"%SOURCE
#某话题下讨论列表请求url
BASE_URL="https://www.zhihu.com/api/v4/topics/%s/feeds/timeline_activity"
#初始请求url附带的请求参数
URL_QUERY="?include=data%5B%3F%28target.type%3Dtopic_sticky_module%29%5D.target.data%5B%3F%28target.type%3Danswer%29%5D.target.content%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%3Bdata%5B%3F%28target.type%3Dtopic_sticky_module%29%5D.target.data%5B%3F%28target.type%3Danswer%29%5D.target.is_normal%2Ccomment_count%2Cvoteup_count%2Ccontent%2Crelevant_info%2Cexcerpt.author.badge%5B%3F%28type%3Dbest_answerer%29%5D.topics%3Bdata%5B%3F%28target.type%3Dtopic_sticky_module%29%5D.target.data%5B%3F%28target.type%3Darticle%29%5D.target.content%2Cvoteup_count%2Ccomment_count%2Cvoting%2Cauthor.badge%5B%3F%28type%3Dbest_answerer%29%5D.topics%3Bdata%5B%3F%28target.type%3Dtopic_sticky_module%29%5D.target.data%5B%3F%28target.type%3Dpeople%29%5D.target.answer_count%2Carticles_count%2Cgender%2Cfollower_count%2Cis_followed%2Cis_following%2Cbadge%5B%3F%28type%3Dbest_answerer%29%5D.topics%3Bdata%5B%3F%28target.type%3Danswer%29%5D.target.content%2Crelationship.is_authorized%2Cis_author%2Cvoting%2Cis_thanked%2Cis_nothelp%3Bdata%5B%3F%28target.type%3Danswer%29%5D.target.author.badge%5B%3F%28type%3Dbest_answerer%29%5D.topics%3Bdata%5B%3F%28target.type%3Darticle%29%5D.target.content%2Cauthor.badge%5B%3F%28type%3Dbest_answerer%29%5D.topics%3Bdata%5B%3F%28target.type%3Dquestion%29%5D.target.comment_count&limit="+str(
LIMIT)
HEADERS={
"User-Agent":USER_AGENT,
"Referer":REFERER,
"authorization":AUTHORIZATION
指定url，获取对应原始内容/图片
deffetch_image(url): try: response=requests.get(url,headers=HEADERS) exceptExceptionase: raisee returnresponse.content
指定url，获取对应JSON返回/话题列表
deffetch_activities(url): try: response=requests.get(url,headers=HEADERS) exceptExceptionase: raisee returnresponse.json()
处理返回的话题列表
defparser_activities(datums,face_detective):
fordataindatums["data"]:
target=data["target"]
if"content"notintargetor"question"notintargetor"author"notintarget:
continue
html=etree.HTML(target["content"])
seq=0
title=target["question"]["title"]
author=target["author"]["name"]
images=html.xpath("//img/@src")
forimageinimages:
ifnotimage.startswith("http"):
continue
image_data=fetch_image(image)
score=face_detective(image_data)
ifnotscore:
continue
name="{}--{}--{}--{}.jpg".format(score,author,title,seq)
seq=seq+1
path=Path(__file__).parent.joinpath("image").joinpath(name)
try:
f=open(path,"wb")
f.write(image_data)
f.flush()
f.close()
print(path)
time.sleep(2)
exceptExceptionase:
continue
ifnotdatums["paging"]["is_end"]:
returndatums["paging"]["next"]
else:
returnNone
初始化颜值检测工具
definit_detective(app_id,api_key,secret_key):
client=AipFace(app_id,api_key,secret_key)
options={"face_field":"age,gender,beauty,qualities"}
defdetective(image):
image=str(base64.b64encode(image),"utf-8")
response=client.detect(str(image),"BASE64",options)
response=response.get("result")
ifnotresponse:
return
if(notresponse)or(response["face_num"]==0):
return
face_list=response["face_list"]
ifpydash.get(face_list,"0.face_probability")<0.6:
return
ifpydash.get(face_list,"0.beauty")
程序入口
defmain():
face_detective=init_detective(APP_ID,API_KEY,SECRET_KEY)
url=BASE_URL%SOURCE+URL_QUERY
whileurlisnotNone:
datums=fetch_activities(url)
url=parser_activities(datums,face_detective)
time.sleep(5)
if__name__=='__main__':
main()
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持毛票票。