https://tiku.fenbi.com/api/xingce/questions
https://tiku.fenbi.com/api/xingce/solutions

##導(dǎo)包
import requests
import lxml.etree
import re
import time
import os
from docx import Document
from docx.shared import Inches
from docx.shared import Pt
from docx.shared import Inches
from docx.oxml.ns import qn
from docx.enum.text import WD_ALIGN_PARAGRAPH
url = str(input("請輸入練習(xí)的網(wǎng)址："))
headers={
###完整的headers，否則獲取不到數(shù)據(jù)
}
response = requests.get(url = url,headers = headers)
response.encoding='utf-8'
reptext = response.text
tree = lxml.etree.HTML(reptext) #解析網(wǎng)站獲取源碼

dirName="考公圖片"
if not os.path.exists(dirName):
 os.mkdir(dirName) #網(wǎng)站圖片保存路徑
 
jiexi = re.findall(r'<div class="jiexi-item-title">解析.*?。</div>.*?</div>', reptext,re.S) #獲取題目解析

imgg = []
for each in jiexi:
 imgg.append(re.findall(r'<img src="(.*?)".*?>', each)) #獲取解析里的圖片URL
 
imgt = []
for each in imgg:
 if each == []:
  imgt.append([1])
 else:
  imgt.append(each) #把解析里圖片URL美化整理一下
  
jiexilast = []
for qq in jiexi:
 jiexilast.append(re.sub(r'<[^>]+>', '', qq)) #美化題目解析
 
corrected = re.findall(r'<span class="g-right-answer-color">[a-zA-Z]{1,4}</span>', reptext) #獲取正確答案
correct = []
for ee in corrected:
 correct.append(re.sub(r'<[^>]+>', '', ee)) #美化正確答案
 
yoursed = re.findall(r'<span class="yellowWord">[a-zA-Z]{1,4}</span>', reptext) #獲取自己的答案
yours = []
for ee in yoursed:
 yours.append(re.sub(r'<[^>]+>', '', ee)) #美化自己的答案
 
timuleixing = re.findall(r'<span class="greenWord">(.*?)</span>.*?</div>',reptext,re.S) #獲取題目類型

find1 = re.findall(r'<span class="greenWord">.*?</span>(.*?)</div>',reptext,re.S)
for each in find1:
 re.sub(r'<.*?>','',each)
find5 = [] #最終的題目
for each in find1:
 find5.append(re.sub(r'<[^>]+>', '', each))
 
img = []
for each in find1:
 img.append(re.findall(r'<img src="(.*?)".*?>', each))
imgx = []
for each in img:
 if each == []:
  imgx.append([1])
 else:
  imgx.append(each) #最終版題目圖片URL
  

v = tree.xpath('//div[@class="exercise-main-title"]//text()') #本次題目類型

try:
 ###這是既有復(fù)合題也有單選題的
 fuheti = re.findall(r'<!--復(fù)合題-->(.*?)<div class="exercise-main-topics"',reptext,re.S)[0].split('<!--復(fù)合題-->')
except:
 try:
  ###這是只有復(fù)合題或者復(fù)合題在最后幾題的
  fuheti = re.findall(r'<!--復(fù)合題-->(.*?)<!-- 糾錯的彈窗 -->',reptext,re.S)[0].split('<!--復(fù)合題-->')
 except:
  pass
count = 0

###導(dǎo)入標(biāo)題
document = Document()
p = document.add_paragraph()
p.paragraph_format.alignment = WD_ALIGN_PARAGRAPH.CENTER
run = p.add_run(v[0][5:-3])
run.font.size = Pt(14)
run.font.name=u'宋體'
r = run._element
r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
choose = []

###處理題目選項
axuanxiang = []
bxuanxiang = []
cxuanxiang = []
dxuanxiang = []
xuanxiang = re.findall(r'<div class="main-topic-choices">(.*?)<div class="main-topic-letters clearfix pl14">',reptext,re.S)
for everything in xuanxiang:
 try: ##處理只有兩個選項
  axuanxiang.append(re.sub("<.*?>","",re.findall(r'<div.*?class.*?main-topic-choice.*?>(A.*?)</div>',everything,re.S)[0]))
 except:
  axuanxiang.append('--')
 try:
  bxuanxiang.append(re.sub("<.*?>","",re.findall(r'<div.*?class.*?main-topic-choice.*?>(B.*?)</div>',everything,re.S)[0]))
 except:
  bxuanxiang.append('--')
 try:
  cxuanxiang.append(re.sub("<.*?>","",re.findall(r'<div.*?class.*?main-topic-choice.*?>(C.*?)</div>',everything,re.S)[0]))
 except:
  cxuanxiang.append('--')
 try:
  dxuanxiang.append(re.sub("<.*?>","",re.findall(r'<div.*?class.*?main-topic-choice.*?>(D.*?)</div>',everything,re.S)[0]))
 except:
  dxuanxiang.append('--')
  

 
for every in correct:
 if every != yours[count]:
  ###處理復(fù)合題題目
  try:
   for eacy in fuheti:
    if find5[count] in eacy:
     fuheti_URL = re.findall(r'<img src="(.*?)".*?>',re.findall(r'.*?<p>(.*?)</p>',eacy,re.S)[0],re.S)
     fuheti_last = re.sub(r'<.*?>','',re.findall(r'.*?<p>(.*?)</p>',eacy,re.S)[0])
     fuheti_last = re.sub(r'\xa0\xa0\xa0\xa0\xa0\xa0\xa0','\n',fuheti_last)
     if fuheti_last not in choose:
      p = document.add_paragraph()
      run = p.add_run(fuheti_last)
      run.font.size = Pt(14)
      run.font.name=u'宋體'
      r = run._element
      r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
      headers ={
     'Use-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'
       }
      for eacu in fuheti_URL:
       img_data = requests.get(url = eacu,headers = headers).content
       img_path = dirName+'/'+'tupian'+'.jpg'
       with open(img_path,'wb') as fp:
        fp.write(img_data)
        print("保存成功")
       document.add_picture(img_path, width=Inches(5))
      choose.append(fuheti_last)
  except:
   pass
  
  ###導(dǎo)入單選題題目
  p = document.add_paragraph()
  run = p.add_run(str(count+1)+"、"+timuleixing[count]+find5[count][3:])
  run.font.size = Pt(14)
  run.font.name=u'宋體'
  r = run._element
  r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
  url = imgx[count][0]
  headers ={
   'Use-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'
  }
  try:
   img_data = requests.get(url = url,headers = headers).content
   img_path = dirName+'/'+'tupian'+'.jpg'
   with open(img_path,'wb') as fp:
    fp.write(img_data)
    print("保存成功")
   document.add_picture(img_path, width=Inches(5))
   count+=1
  except:
   count+=1
   
  ###導(dǎo)入選項
  p = document.add_paragraph()
  run = p.add_run(axuanxiang[count-1])
  run.font.size = Pt(14)
  run.font.name=u'宋體'
  r = run._element
  r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
  p = document.add_paragraph()
  run = p.add_run(bxuanxiang[count-1])
  run.font.size = Pt(14)
  run.font.name=u'宋體'
  r = run._element
  r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
  p = document.add_paragraph()
  run = p.add_run(cxuanxiang[count-1])
  run.font.size = Pt(14)
  run.font.name=u'宋體'
  r = run._element
  r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
  p = document.add_paragraph()
  run = p.add_run(dxuanxiang[count-1])
  run.font.size = Pt(14)
  run.font.name=u'宋體'
  r = run._element
  r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
  p = document.add_paragraph()
  run = p.add_run("\n")
  run.font.size = Pt(14)
  run.font.name=u'宋體'
  r = run._element
  r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
  
 else:
  count+=1

###美化界面
p = document.add_paragraph()
run = p.add_run("\n\n\n\n\n")
run.font.size = Pt(14)
run.font.name=u'宋體'
r = run._element
r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')

###美化解析
counting = 0
jiexilast2 = []
for ok in jiexilast:
 jiexilast2.append(re.sub(r'\n\t\t','：',ok))
for every in correct:
 if every != yours[counting]:
  ###導(dǎo)入解析和答案
  p = document.add_paragraph()
  run = p.add_run(str(counting+1)+"、"+"正確答案為："+correct[counting]+"\n"+jiexilast2[counting])
  run.font.size = Pt(14)
  run.font.name=u'宋體'
  r = run._element
  r.rPr.rFonts.set(qn('w:eastAsia'),u'宋體')
  url = imgt[counting][0]
  headers ={
   'Use-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'
  }
  try:
   img_data = requests.get(url = url,headers = headers).content
   img_path = dirName+'/'+'tupian'+'.jpg'
   with open(img_path,'wb') as fp:
    fp.write(img_data)
    print("保存成功")
   document.add_picture(img_path, width=Inches(5))
   print("寫入成功")
   counting+=1
  except:
   counting+=1
 else:
  counting+=1
###保存文檔
document.save(v[0][5:-3]+'.docx')
print(v[0][5:-3]+'保存成功！')