Crawler｜Python explore des photos de filles de la station B, motivation pour apprendre !

# 导包
import re
import time
import json
import random
import requests
from fake_useragent import UserAgent

# 获取页面信息
def get_datas(url,headers):
    r = requests.get(url, headers=headers)
    r.raise_for_status()
    r.encoding = chardet.detect(r.content)['encoding'] 
    datas = json.loads(r.text)
    return datas

# 获取图片链接信息
def get_hrefs(datas):
    titles,hrefs = [],[]
    for data in datas['data']['result']:
        # 标题
        title = data['title']
        # 时长
        duration = data['duration']
        # 播放量
        video_review =data['video_review']
        # 发布时间
        date_rls = data['pubdate']
        pubdate = time.strftime('%Y-%m-%d %H:%M', time.localtime(date_rls))
        # 作者
        author = data['author']
        # 图片链接
        link_pic = data['pic']
        href_pic = 'https:' + link_pic
        
        titles.append(title)
        hrefs.append(href_pic)
        
        return titles, hrefs

# 保存图片
def download_jpg(titles, hrefs):
    path = "D:/B站小姐姐/"
    if not os.path.exists(path):
        os.mkdir(path)
    for i in range(len(hrefs)):
        title_t = titles[i].replace('/','').replace('，','').replace('?','')
     title_t = title_t.replace(' ','').replace('|','').replace('。','')
        filename = '{}{}.jpg'.format(path,title_t)
        with open(filename, 'wb') as f:
            req = requests.get(url=hrefs[i], headers=headers)
            f.write(req.content)
            time.sleep(random.uniform(1.5,3.4))