def findPage():
http,ua = getHttpUa()
conn,cur = getCursor()
dlList = getResult(sltCollNotNull,cur)
for dl in dlList:
# this is test!!!! read from a txt
#html = readTXT('E:/Code/Test Data/Paul Robert Barford - ACM author profile page - colleagues.txt')
#html = readTXT('E:/Code/Test Data/Yu Zheng - ACM author profile page.txt')
#html = readTXT('E:/Code/Test Data/A. Smolic - ACM author profile page.txt')
if ChangeOrNot() == True:
editeProxies(http)
editeHeader(ua)
time.sleep(random.randint(1, 12))
html = str(getPage(dl['colleage']))#取出url
if html != ' ':
nameLink = analysisPage(html)
for nl in nameLink:
addInfo(conn,cur,nl)
#print(nl)
print('Now is '+str(dl['id']))
#break#only run one time
cur.close()
conn.close()
def run(self):
while True:
# 从队列中获取任务并扩展tuple
httpProxies = commHttpProxies.copy()
headers = commHeaders.copy()
cookies = commCookies.copy()
dl = self.dlQueue.get()
http = self.ipQueue.get()
ua = self.uaQueue.get()
httpProxies['https'] = http
#修饰参数
if ChangeOrNot() == True:#随机触发
headers=editeHeader(ua,headers,dl['name'])#改变user agent
cookies=editeCookies(cookies)
time.sleep(random.randint(5, 20))#随机休眠
#取出html
html = str(getPage(dl['url'],httpProxies,headers,cookies))#取出url
papercsv = getCsvUrl(html)
dl['papercsv'] = papercsv
#放回
self.ipQueue.put(http)
self.uaQueue.put(ua)
if html == ' ':#未获取成功，重新放入
self.dlQueue.put(dl)
#放入
else:
print('get: '+dl['id'])
self.htmlQueue.put(dl)
self.dlQueue.task_done()
def run(self):
while True:
# Get the work from the queue and expand the tuple
# 从队列中获取任务并扩展tuple
httpProxies = commHttpProxies.copy()
headers = commHeaders.copy()
cookies = commCookies.copy()
dl = self.dlQueue.get()
http = self.ipQueue.get()
ua = self.uaQueue.get()
httpProxies['https'] = http
#ts1 = datetime.datetime.now()
#修饰参数
if ChangeOrNot() == True: #随机触发
#httpProxies=editeProxies(http,httpProxies)#改变http
headers = editeHeader(ua, headers, dl['name']) #改变user agent
cookies = editeCookies(cookies)
time.sleep(random.randint(5, 20)) #随机休眠
#取出html
html = str(getPage(dl['url'], httpProxies, headers,
cookies)) #取出url
#放回
self.ipQueue.put(http)
self.uaQueue.put(ua)
if html == ' ': #未获取成功，重新放入
self.dlQueue.put(dl)
#放入
self.htmlQueue.put((html, dl))
#print('get: '+str(dl['id']))
#ts2 = datetime.datetime.now()
#print('page id:'+str(dl['id'])+' time:'+str(ts2-ts1))
self.dlQueue.task_done()
def run(self):
while True:
# 从队列中获取任务并扩展tuple
httpProxies = commHttpProxies.copy()
headers = commHeaders.copy()
cookies = commCookies.copy()
ua = self.uaQueue.get()
dl = self.htmlQueue.get()
http = self.ipQueue.get()
httpProxies['https'] = http
#修饰参数
if ChangeOrNot() == True:#随机触发
headers=editeHeader(ua,headers,dl['name'])#改变user agent
cookies=editeCookies(cookies)
time.sleep(random.randint(6, 15))#随机休眠
#-----------------------------这里就是不一样的地方
#取出csv
flag = findCSV(dl,httpProxies,headers,cookies)#取出url
self.ipQueue.put(http)#放回
self.uaQueue.put(ua)
if not flag:#未获取成功，重新放入
self.htmlQueue.put(dl)
#放入
self.htmlQueue.task_done()
def run(self):
while True:
# Get the work from the queue and expand the tuple
# 从队列中获取任务并扩展tuple
httpProxies = commHttpProxies.copy()
headers = commHeaders.copy()
cookies = commCookies.copy()
ua = self.uaQueue.get()
dl = self.dlQueue.get()
http = self.ipQueue.get()
httpProxies['https'] = http
#ts1 = datetime.datetime.now()
#修饰参数
if ChangeOrNot() == True: #随机触发
#httpProxies=editeProxies(http,httpProxies)#改变http
headers = editeHeader(ua, headers, dl['name']) #改变user agent
cookies = editeCookies(cookies)
time.sleep(random.randint(7, 15)) #随机休眠
#取出html
flag = findCSV(dl, httpProxies, headers, cookies) #取出url
#html = readTXT('E:/Code/Test Data/Yu Zheng - ACM author profile page.txt')
self.ipQueue.put(http) #放回
self.uaQueue.put(ua)
if not flag: #未获取成功，重新放入
self.dlQueue.put(dl)
#放入
#print('get: '+str(dl['id']))
#ts2 = datetime.datetime.now()
#print('page id:'+str(dl['id'])+' time:'+str(ts2-ts1))
self.dlQueue.task_done()
def findCSV():
httpProxies = commHttpProxies
headers = commHeaders
http,ua = getHttpUa()#获取伪装的备选http，userAgent列表
conn,cur = getCursor()#获取数据库连接和游标
dlList = getResult(sltDLNotCom,cur)#返回url实体的二维数组
for dl in dlList:
if ChangeOrNot() == True:#随机触发
httpProxies=editeProxies(http,httpProxies)#改变http
headers=editeHeader(ua,headers)#改变user agent
time.sleep(random.randint(1, 12))#随机休眠
url = dl['papercsv']
if url != None and len(url)> 15:
try:
r = requests.get(url, proxies = httpProxies, headers = headers, timeout=30)
if r.status_code == 200:
csv_path = file_path+str(dl['id'])+'.csv'
with open(csv_path,'wb') as csv:
csv.write(r.content)
print('Now is '+str(dl['id']))
except requests.RequestException as e:
print(e)
httpProxies=editeProxies(http,httpProxies)#改变http
headers=editeHeader(ua,headers)#改变user agent
time.sleep(random.randint(1, 12))#随机休眠
try:
r = requests.get(url, proxies = httpProxies, headers = headers, timeout=30)
if r.status_code == 200:
csv_path = file_path+str(dl['id'])+'.csv'
with open(csv_path,'wb') as csv:
csv.write(r.content)
print('Now is '+str(dl['id']))
except Exception:
print('another try is failed! id:'+str(dl['id']))
#break# only run one time
cur.close()
conn.close()
def findPage():
httpProxies = commHttpProxies.copy()
headers = commHeaders.copy()
cookies = commCookies.copy()
#从数据库中获取预访问的url列表，循环访问url地址
http, ua = getHttpUa() #获取伪装的备选http，userAgent列表
conn, cur = getCursor() #获取数据库连接和游标
dlList = getResult(sltDLNotCom, cur) #返回url实体的二维数组
#for i in range(15):
#i = 0
for dl in dlList:
# this is test!!!! read from a txt
#html = readTXT('E:/Code/Test Data/Hsinchun Chen.txt')
#html = readTXT('E:/Code/Test Data/Yu Zheng - ACM author profile page.txt')
#html = readTXT('E:/Code/Test Data/A. Smolic - ACM author profile page.txt')
if ChangeOrNot() == True: #随机触发
httpProxies = editeProxies(http, httpProxies) #改变http
headers = editeHeader(ua, headers, dl['name']) #改变user agent
cookies = editeCookies(cookies)
time.sleep(random.randint(2, 12)) #随机休眠
print(str(httpProxies['https']))
print(str(headers['User-Agent']))
print(str(headers['Referer']))
print(str(cookies['CFID']))
print()
'''
html = str(getPage(dl['url'],httpProxies,headers,cookies))#取出url
if html != ' ':
infoSet = analysisPage(html,int(dl['id']))#分析页面
addInfo(conn,cur,infoSet,dl)#存入数据库
cur.execute('update dlurl1 set status=1 where id='+str(dl['id']))#标记已抽取
conn.commit()
print('Now is '+str(dl['id']))
#break#only run one time
'''
cur.close()
conn.close()
def run(self):
while True:
httpProxies = commHttpProxies.copy()
headers = commHeaders.copy()
cookies = commCookies.copy()
dl = self.dlQueue.get()
http = self.ipQueue.get()
ua = self.uaQueue.get()
httpProxies['https'] = http
#ts1 = datetime.datetime.now()
#修饰参数
if ChangeOrNot() == True:#随机触发
headers=editeHeader(ua,headers,dl['name'])#改变user agent
cookies=editeCookies(cookies)
time.sleep(random.randint(3, 14))#随机休眠
#Optional
dl['colleage'] = cleanURL(dl['colleage'])#delete cookies
#if '&CFID=716005087&CFTOKEN=29677367' in dl['colleage']:
# dl['colleage'] = dl['colleage'].replace('&CFID=716005087&CFTOKEN=29677367','')
#取出html
html = str(getPage(dl['colleage'],httpProxies,headers,cookies))#取出url
#放回
self.ipQueue.put(http)
self.uaQueue.put(ua)
if html == ' ':#未获取成功，重新放入
self.dlQueue.put(dl)
#放入
print('get HTML:'+str(dl['id']))
self.htmlQueue.put((html,dl))
#print('get: '+str(dl['id']))
#ts2 = datetime.datetime.now()
#print('page id:'+str(dl['id'])+' time:'+str(ts2-ts1))
self.dlQueue.task_done()
dlQueue.put(dl)
httpProxies = commHttpProxies.copy()
headers = commHeaders.copy()
cookies = commCookies.copy()
while not dlQueue.empty():
dl = dlQueue.get()
http = random.choice(http)
ua = random.choice(uag)
httpProxies['https'] = http
#ts1 = datetime.datetime.now()
#修饰参数
if ChangeOrNot() == True: #随机触发
headers = editeHeader(ua, headers, dl['name']) #改变user agent
cookies = editeCookies(cookies)
time.sleep(random.randint(5, 20)) #随机休眠
#取出html
html = str(getPage(dl['url'], httpProxies, headers, cookies)) #取出url
#放回
if html == ' ': #未获取成功，重新放入
dlQueue.put(dl)
#放入文件中
try:
path = dirPath + str(dl['id']) + '.txt'
writeTXT(path, html)
print('complete: ' + str(dl['id']))
except Exception:
from tool import signal,getHttpUa,httpProxies,headers,readTXT,getCursor,getResult,ChangeOrNot,editeProxies,editeHeader,getPage
import time
import random
from bs4 import BeautifulSoup
#主要的循环方法
def findSubject():
http,ua = getHttpUa()
conn,cur = getCursor()
subList = getResult(sltDLNotCom,cur)#返回二维数组
for dl in dlList:
# this is test!!!! read from a txt
#html = readTXT('E:/Code/Test Data/Paul Robert Barford - ACM author profile page.txt')
if ChangeOrNot() == True:
editeProxies(http)
editeHeader(ua)
time.sleep(random.randint(1, 20))
html = str(getPage(dl['subject']))#取出url
if html != ' ':
subject = extractSubject(html)
status = addInfo(conn,cur,subject,dl['id'])
if status == 1:
print('Now is '+str(dl['id']))
cur.close()
conn.close()
def extractSubject(doc):
#
combineStr = ''
