爬虫养成记--顺藤摸瓜回首掏（女生定制篇）

:authority: www.nanrentu.cc
:method: GET   // 自定义请求头 请求方法
:path: /sgtp/  // 自定义请求头 请求路径
:scheme: https // 自定义请求头 请求方式
// 所接受的内容格式
accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9
// 所接受的编码方式
accept-encoding: gzip, deflate, br
// 所接受的语言
accept-language: zh-CN,zh;q=0.9
// 缓存控制：告诉服务器客户端希望得到一个最新的资源
cache-control: max-age=0
cookie: UM_distinctid=170a5a00fa25bf-075185606c88b7-396d7407-100200-170a5a00fa3507; Hm_lvt_45e50d2aec057f43a3112beaf7f00179=1583326696,1583756661; CNZZDATA1274895726=1196969733-1583323670-%7C1583752625; Hm_lpvt_45e50d2aec057f43a3112beaf7f00179=1583756721
sec-fetch-dest: document
sec-fetch-mode: navigate
sec-fetch-site: none
sec-fetch-user: ?1
// 屏蔽HTTPS页面出现HTTP请求警报
upgrade-insecure-requests: 1
user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36

// 建立一个名叫headers的字典
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36',
    'cookie': 'UM_distinctid=170a5a00fa25bf-075185606c88b7-396d7407-100200-170a5a00fa3507; CNZZDATA1274895726=1196969733-1583323670-%7C1583925652; Hm_lvt_45e50d2aec057f43a3112beaf7f00179=1583326696,1583756661,1583926583; Hm_lpvt_45e50d2aec057f43a3112beaf7f00179=1583926583'
}
// 发送请求时带上请求头
response = requests.get(baseUrl,headers=headers)

import requests
from pyquery import PyQuery as pq
import uuid

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36',
    'cookie': 'UM_distinctid=170a5a00fa25bf-075185606c88b7-396d7407-100200-170a5a00fa3507; CNZZDATA1274895726=1196969733-1583323670-%7C1583925652; Hm_lvt_45e50d2aec057f43a3112beaf7f00179=1583326696,1583756661,1583926583; Hm_lpvt_45e50d2aec057f43a3112beaf7f00179=1583926583'
}
def saveImage(imgUrl,name):
    imgResponse = requests.get(imgUrl)
    fileName = "学习文件/%s.jpg" % name
    if imgResponse.status_code == 200:
        with open(fileName, 'wb') as f:
            f.write(imgResponse.content)
            f.close()

def getPic(urlArray):
    for url in urlArray:
        res = requests.get(url,headers=headers)
        if res.status_code == 200:
            doc = pq(res.text)
            imgSrc = doc('.info-pic-list > a > img').attr('src')
            print(imgSrc)
            saveImage(imgSrc,uuid.uuid1().hex)
    

def createUrl(indexUrl,allPage):
    baseUrl = indexUrl.split('.html')[0]
    urlArray = []
    for i in range(1,allPage):
        tempUrl = baseUrl+"_"+str(i)+".html"
        urlArray.append(tempUrl)
    return urlArray

def getBoys(link):
    # 摸瓜第1步：获取首页连接
    picIndex = link.attr('href')
    #  摸瓜第2步：打开首页，提取末页链接，得出组图页数
    res = requests.get(picIndex,headers=headers)
    print("当前正在抓取的 picIndex: " + picIndex)
    if res.status_code == 200:
        with open("picIndex.html",'w',encoding="utf-8") as f:
            f.write(res.text)
        doc = pq(res.text)
        lastLink = doc('.page > ul > li:nth-last-child(2) > a').attr('href')
        # 字符串分割，得出全部的页数
        if(lastLink is None):
            return
        # 以.html 为分割符进行分割，取结果数组中的第一项
        temp = lastLink.split('.html')[0]
        # 再以下划线 _ 分割，取结果数组中的第二项,再转为数值型
        allPage = int(temp.split('_')[1])
        # 摸瓜第3步：根据首尾链接构造url
        urlArray = createUrl(picIndex,allPage)
        # 摸瓜第4步：存储图片，摸瓜成功
        getPic(urlArray)

def main():
    baseUrl = "https://www.nanrentu.cc/sgtp/"
    response = requests.get(baseUrl,headers=headers)
    if response.status_code == 200:
        with open("index.html",'w',encoding="utf-8") as f:
            f.write(response.text)
        doc = pq(response.text)
        # 得到所有图集的标题连接
        titleLinks = doc('.h-piclist > li > a').items()
        # 遍历这些连接
        for link in titleLinks:
            getBoys(link)

if __name__ == "__main__":
    main()

● 1.5万字概括ES6全部特性● 妙用CSS变量，让你的CSS变得更心动● 拒绝删库跑路！上手 Docker 容器数据管理