python实现知乎高颜值图片爬取

import time
import pydash
import base64
import requests
from lxml import etree
from aip import AipFace
from pathlib import Path

#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 = "oauth c3cef7c66a1843f8b3a9e6a1e3160e20"
# 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

# 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"

USER_AGENT = "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/534.55.3 (KHTML, like Gecko) Version/5.1.5 Safari/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 = "" + str(
  LIMIT)

HEADERS = {
  "User-Agent": USER_AGENT,
  "Referer": REFERER,
  "authorization": AUTHORIZATION

def fetch_image(url):
  try:
    response = requests.get(url, headers=HEADERS)
  except Exception as e:
    raise e
  return response.content

def fetch_activities(url):
  try:
    response = requests.get(url, headers=HEADERS)
  except Exception as e:
    raise e
  return response.json()

def parser_activities(datums, face_detective):
  for data in datums["data"]:
    target = data["target"]
    if "content" not in target or "question" not in target or "author" not in target:
      continue
    html = etree.HTML(target["content"])
    seq = 0
    title = target["question"]["title"]
    author = target["author"]["name"]
    images = html.xpath("//img/@src")
    for image in images:
      if not image.startswith("http"):
        continue
      image_data = fetch_image(image)
      score = face_detective(image_data)
      if not score:
        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)
      except Exception as e:
        continue
  if not datums["paging"]["is_end"]:
    return datums["paging"]["next"]
  else:
    return None

def init_detective(app_id, api_key, secret_key):
  client = AipFace(app_id, api_key, secret_key)
  options = {"face_field": "age,gender,beauty,qualities"}
  def detective(image):
    image = str(base64.b64encode(image), "utf-8")
    response = client.detect(str(image), "BASE64", options)
    response = response.get("result")
    if not response:
      return
    if (not response) or (response["face_num"] == 0):
      return
    face_list = response["face_list"]
    if pydash.get(face_list, "0.face_probability") < 0.6:
      return
    if pydash.get(face_list, "0.beauty") < BEAUTY_THRESHOLD:
      return
    if pydash.get(face_list, "0.gender.type") != "female":
      return
    score = pydash.get(face_list, "0.beauty")
    return score
  return detective

def main():
  face_detective = init_detective(APP_ID, API_KEY, SECRET_KEY)
  url = BASE_URL % SOURCE + URL_QUERY
  while url is not None:
    datums = fetch_activities(url)
    url = parser_activities(datums, face_detective)
    time.sleep(5)
if __name__ == '__main__':
  main()