import requests
from lxml import etree #etree
import urllib.parse
import re

header = {
    "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"
}
def suibian(url):
    respones = requests.get(url,headers=header)
    a = etree.HTML(respones.
 
text)
    b = a.xpath('//ul[@class="note-list"]/li')
    for i in b:
        print(i)
        a_O = i.xpath('.//a[@class="title"]/@href')[0]
        d = urllib.parse.urljoin(respones.url,a_O)
        print(d)
        jiexi(d)
def jiexi(url):
    response = requests.get(url,headers=header)
    a = etree.HTML(
 
response.text)
    b = a.xpath('//h1[@class="title"]/text()')
    c = a.xpath('//span[@class="name"]/a/text()')
    d = a.xpath('//div[@class="meta"]//text()')
    e = a.xpath('//div[@class="show-content"]//img/@data-original-src')
    f = a.xpath('//div[@class="show-content"]//text()')
    for i in e:
        url = i.
 
replace('//','https://')
        img(url,b)
    for i in f:
        writes(i,b)


def img(url,b):
    response = requests.get(url,headers=header)
    r = re.compile(".*-(.{1,15})",re.S)
    c = r.findall(response.url)[0]
    # print(c)
    with open('{}{}.jpg'.format(b,c),'wb') as f:
        f.write(response.content)
def writes(t,b):
    with open('{}.txt'.format(b),'a') as f:
        f.write(t)



   








if __name__ == '__main__':
    url ="https://www.jianshu.com/c/7b2be866f564?order_by=added_at&page=1"  
    suibian(url)