這是一個稍微復雜的demo,它的功能如下:
- 輸入專利號,下載對應的專利文檔
- 輸入關鍵詞,下載所有相關的專利文檔
0. 模塊准備
- 首先是requests,這個就不說了,爬蟲利器
- 其次是安裝tesseract-ocr,pytesseract 和 PIL 「用於識別驗證碼」
1. 模擬登陸
我們需要對 這個網站 專利檢索及分析 進行分析,反復鼓搗之后發現,找不到下載鏈接?
tell my why? 原來是沒有登陸。 果然,登陸之后能夠找到下載按鈕,並手動下載成功。
注意到,在登陸和下載的同時,還需要輸入驗證碼。
這樣,我們第一步要解決的問題,便是驗證碼識別與模擬登陸
-
ubuntu下使用:
apt-get install tesseract-ocr
pip install pytesseract
pip install PIL
2. 關鍵字檢索請求
登陸之后,我們鍵入一個關鍵詞,進行檢索
瀏覽器會向上圖所示的url發送post請求,form data
中的searchExp
是我們的關鍵詞
那么,我們通過post請求,便可以得到檢索結果了
3. 翻頁
把鼠標放在下一頁上,我們能看到,是調用js來實現頁面跳轉的。
進一步分析,實際上我們對上圖的url進行post請求也能實現翻頁。
注意到form data
中的參數
"resultPagination.limit":"10",
"resultPagination.sumLimit":"10",
"resultPagination.start":cnt, #這次參數決定了當前頁面從搜索到的第幾個數據開始
"resultPagination.totalCount":total, #總的搜索數據數目
"searchCondition.searchType":"Sino_foreign",
"searchCondition.dbId":"",
"searchCondition.extendInfo['MODE']":"MODE_GENERAL",
"searchCondition.searchExp":keywords, #我們輸入的關鍵詞
"wee.bizlog.modulelevel":"0200101",
"searchCondition.executableSearchExp":executableSearchExp, #需要我們自己構造
"searchCondition.literatureSF":literatureSF, #需要我們自己構造
"searchCondition.strategy":"",
"searchCondition.searchKeywords":"",
"searchCondition.searchKeywords":keywords # 我們輸入的關鍵詞
所以我們需要翻頁的時候向
showSearchResult-startWa.shtml
這個頁面進行post請求即可,
注意每次更新resultPagination.start
參數
4. 瀏覽文檔
需要下載專利文獻,我們需要跳轉到另外一個頁面,而這個頁面,又是通過js跳轉的。
注意這里跳轉的同時,傳入的參數即為專利號,我們把它們保存下了,后面的post請求需要用到
可以看到,通過js跳轉到了一個新窗口showViewList
這里的viewQC.viewLiteraQCList[0].searchCondition.executableSearchExp:
非常關鍵,
這正是之前將它們保存下來的原因。
'viewQC.viewLiteraQCList[0].srcCnName':cnName,
'viewQC.viewLiteraQCList[0].srcEnName':srcEnName,
'viewQC.viewLiteraQCList[0].searchStrategy':'',
'viewQC.viewLiteraQCList[0].searchCondition.executableSearchExp':condition,
'viewQC.viewLiteraQCList[0].searchCondition.sortFields':'-APD,+PD',
'viewQC.needSearch':'true',
'viewQC.type':'SEARCH',
'wee.bizlog.modulelevel':'0200604'
5. 下載文檔
點擊下載按鈕,彈出一個新的界面,Nextwork中產生三個請求
第三個便是驗證碼對應的圖片
手動輸入驗證碼后,首先通過
validateMask.shtml
進行驗證碼校驗,並返回一個加密過后的mask串
再向downloadLitera.do
發送post請求,完成下載!其中的參數,需要在之前自行確定。
6. 初步代碼
很多細節問題需要考慮,這份代碼只能算初步代碼:
#coding=utf-8
import requests, re
import Image
from pytesseract import *
def get_verification_code(url):
src = s.get(url).content
open('temp_pic',"wb").write(src)
pic=Image.open(r'./temp_pic')
return image_to_string(pic)
login_url = 'http://www.pss-system.gov.cn/sipopublicsearch/wee/platform/wee_security_check'
host_url = 'http://www.pss-system.gov.cn/sipopublicsearch/portal/index.shtml'
pic_url = 'http://www.pss-system.gov.cn/sipopublicsearch/portal/login-showPic.shtml'
pic_mask = 'http://www.pss-system.gov.cn/sipopublicsearch/search/validateCode-showPic.shtml?params=2595D550022F3AC2E5D76ED4CAFD4D8E'
search_url = 'http://www.pss-system.gov.cn/sipopublicsearch/search/smartSearch-executeSmartSearch.shtml'
show_page = 'http://www.pss-system.gov.cn/sipopublicsearch/search/showSearchResult-startWa.shtml'
show_list = 'http://www.pss-system.gov.cn/sipopublicsearch/search/search/showViewList.shtml'
mask_check_url = 'http://www.pss-system.gov.cn/sipopublicsearch/search/validateMask.shtml'
download_url = 'http://www.pss-system.gov.cn/sipopublicsearch/search/downloadLitera.do'
down_head = {
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate',
'Accept-Language':'en-US,en;q=0.8',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Content-Type':'application/x-www-form-urlencoded',
'Origin':'http://www.pss-system.gov.cn',
'Referer':'http://www.pss-system.gov.cn/sipopublicsearch/search/search/showViewList.shtml',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.75 Safari/537.36'
}
s = requests.session()
cookies = dict(cookies_are='working')
s.get(host_url)
vcode = get_verification_code(pic_url)
login_data = {
'j_validation_code':vcode,
'j_loginsuccess_url':'http://www.pss-system.gov.cn/sipopublicsearch/portal/index.shtml',
'j_username':'emhhbmdzYW4xMjM=',
'j_password':'emhhbmdzYW4xMjM='
}
s.post(login_url,data=login_data,cookies=cookies)
print "login!!\n-------------------"
keywords = raw_input("please input keywords: ")
cnt = 0
search_data = {
'searchCondition.searchExp':keywords,
'searchCondition.dbId':'VDB',
'searchCondition.searchType':'Sino_foreign',
'wee.bizlog.modulelevel':'0200101'
}
result = s.post(search_url,data=search_data,cookies=cookies).content
total = int(re.search(r' 共.*?頁 (.*?)條數據',result,re.S).group(1))
print "total:",total
all_result = re.findall('javascript:viewLitera_search\(\'.*?\',\'(.*?)\',\'single\'\)',result,re.S)
executableSearchExp = "VDB:(TBI=" + "'" + keywords + "')"
literatureSF = "復合文本=(" + keywords + ")"
while cnt <= total:
cnt += 10
for cur in all_result:
real_id = cur
if 'CN' in cur :
real_id = cur[:14] + '.' + cur[14:]
condition = r"VDB:(ID='" + real_id + r"')"
cnName = '檢索式:復合文本=' + '(' + keywords + ')'
srcEnName = 'SearchStatement:復合文本=' + '(' + keywords + ')'
print real_id
data_cur = {
'viewQC.viewLiteraQCList[0].srcCnName':cnName,
'viewQC.viewLiteraQCList[0].srcEnName':srcEnName,
'viewQC.viewLiteraQCList[0].searchStrategy':'',
'viewQC.viewLiteraQCList[0].searchCondition.executableSearchExp':condition,
'viewQC.viewLiteraQCList[0].searchCondition.sortFields':'-APD,+PD',
'viewQC.needSearch':'true',
'viewQC.type':'SEARCH',
'wee.bizlog.modulelevel':'0200604'
}
show = s.post(show_list,data = data_cur,cookies=cookies).content
tmp = re.search('literaList\[0\] = \{(.*?)\};',show,re.S)
if tmp == None:
break;
idlist = re.findall('"(.*?)"',tmp.group(1).replace(' ',''),re.S)
# 解析驗證碼
vcode = get_verification_code(pic_mask)
print vcode
# 獲取加密后的mask
mask_data = {
'':'',
'wee.bizlog.modulelevel':'02016',
'mask':vcode
}
kao = s.post(mask_check_url,data=mask_data,cookies=cookies).content
#{"downloadCount":2,"downloadItems":null,"mask":"1a75026a-5138-4460-a35e-5ef60258d1d0","pass":true,"sid":null}
mask_jm = re.search(r'"mask":"(.*?)"',kao,re.S).group(1)
#print mask_jm
data_down = {
'wee.bizlog.modulelevel':'02016',
'checkItems':'abstractCheck',
'__checkbox_checkItems':'abstractCheck',
'checkItems':'TIVIEW',
'checkItems':'APO',
'checkItems':'APD',
'checkItems':'PN',
'checkItems':'PD',
'checkItems':'ICST',
'checkItems':'PAVIEW',
'checkItems':'INVIEW',
'checkItems':'PR',
'checkItems':'ABVIEW',
'checkItems':'ABSIMG',
'idList[0].id':idlist[0],
'idList[0].pn':idlist[3],
'idList[0].an':idlist[2],
'idList[0].lang':idlist[4],
'checkItems':'fullTextCheck',
'__checkbox_checkItems':'fullTextCheck',
'checkItems':'fullImageCheck',
'__checkbox_checkItems':'fullImageCheck',
'mask':mask_jm
}
down_page = s.post(download_url,data=data_down,headers=down_head,cookies=cookies).content
open( cur + ".zip" ,"wb").write(down_page)
kao_data = {
"resultPagination.limit":"10",
"resultPagination.sumLimit":"10",
"resultPagination.start":cnt,
"resultPagination.totalCount":total,
"searchCondition.searchType":"Sino_foreign",
"searchCondition.dbId":"",
"searchCondition.extendInfo['MODE']":"MODE_GENERAL",
"searchCondition.searchExp":keywords,
"wee.bizlog.modulelevel":"0200101",
"searchCondition.executableSearchExp":executableSearchExp,
"searchCondition.literatureSF":literatureSF,
"searchCondition.strategy":"",
"searchCondition.searchKeywords":"",
"searchCondition.searchKeywords":keywords
}
result = s.post(show_page,data=kao_data,cookies=cookies).content
print "next page"
all_result = re.findall('javascript:viewLitera_search\(\'.*?\',\'(.*?)\',\'single\'\)',result,re.S)
7. 效果展示
8. TODO
可能會繼續更新 code