本文實(shí)例講述了Python 實(shí)現(xiàn)的微信爬蟲。分享給大家供大家參考,具體如下:
單線程版:
import urllib.request
import urllib.parse
import urllib.error
import re,time
headers = ("User-Agent",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
operner = urllib.request.build_opener()
operner.addheaders = [headers]
urllib.request.install_opener(operner)
list_url = []
###使用代理獲取網(wǎng)頁url內(nèi)容
def use_proxy(url):
try:
# proxy = urllib.request.ProxyHandler({'http':proxy_addr}) ##使用代理版
# operner = urllib.request.build_opener()
# urllib.request.install_opener(operner)
headers = ("User-Agent",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
operner = urllib.request.build_opener()
operner.addheaders = [headers]
urllib.request.install_opener(operner)
data = urllib.request.urlopen(url).read().decode('utf-8')
# print (data)
return data
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
elif hasattr(e, "reason"):
print(e.reason)
except Exception as e:
print("exception" + str(e))
time.sleep(1)
##獲取要爬取的url
def get_url(key, pagestart, pageend):
try:
keycode = urllib.parse.quote(key)
for page in range(pagestart, pageend + 1):
url = "http://weixin.sogou.com/weixin?query=%s&_sug_type_=&s_from=input&_sug_=n&type=%d&page=1&ie=utf8" % (
keycode, page)
data1 = use_proxy(url)
#print("data1的內(nèi)容是", data1)
listurl_pattern = '
.*?("http://.*?)
'
result = re.compile(listurl_pattern, re.S).findall(data1)
for i in range(len(result)):
res = result[i].replace("amp;", "").split(" ")[0].replace("\"", "")
list_url.append(res)
#print(list_url)
return list_url
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
elif hasattr(e, "reason"):
print(e.reason)
except Exception as e:
print("exception:", e)
##通過獲取的url爬行內(nèi)容數(shù)據(jù)并處理
def get_url_content(list_url):
fh1=open("D:\\python-script\\1.html", 'wb')
html1 = '''\n\n\n
\n
微信文章
\n'''
fh1.write(html1.encode("utf-8"))
fh1.close()
fh = open("D:\\python-script\\1.html", 'ab')
for url in list_url:
data_content = use_proxy(url)
#print (data_content)
#sys.exit()
title_pattern = '
.*?'
result_title = re.compile(title_pattern, re.S).findall(data_content)
##標(biāo)題(str)
res_title = result_title[0].replace("
", "").replace("
",
"").strip()
content_pattern = 'id="js_content">(.*?)
'
content = re.compile(content_pattern, re.S).findall(data_content)
try:
fh.write(res_title.encode("utf-8"))
for i in content:
fh.write(i.strip().encode("utf-8"))
except UnicodeEncodeError as e:
continue
fh.write("".encode("utf-8"))
if __name__ == '__main__':
pagestart = 1
pageend = 2
key = "人工智能"
get_url(key, pagestart, pageend)
get_url_content(list_url)
多線程版:
import urllib.request
import urllib.parse
import urllib.error
import re,time
import queue
import threading
headers = ("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
operner = urllib.request.build_opener()
operner.addheaders = [headers]
urllib.request.install_opener(operner)
urlque = queue.Queue()
list_url = []
###使用代理獲取網(wǎng)頁url內(nèi)容
def use_proxy(url):
try:
# proxy = urllib.request.ProxyHandler({'http':proxy_addr})
# operner = urllib.request.build_opener()
# urllib.request.install_opener(operner)
headers = ("User-Agent",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3107.4 Safari/537.36")
operner = urllib.request.build_opener()
operner.addheaders = [headers]
urllib.request.install_opener(operner)
data = urllib.request.urlopen(url).read().decode('utf-8')
#print (data)
return data
except urllib.error.URLError as e:
if hasattr(e,"code"):
print (e.code)
elif hasattr(e,"reason"):
print (e.reason)
except Exception as e:
print ("exception"+str(e))
time.sleep(1)
###獲取文章的url連接,并將連接加入到隊(duì)列
class get_url(threading.Thread):
def __init__(self,key,pagestart,pageend,urlque):
threading.Thread.__init__(self)
self.pagestart = pagestart
self.pageend = pageend
self.key = key
self.urlque = urlque
def run(self):
try:
keycode = urllib.parse.quote(self.key)
for page in range(self.pagestart,self.pageend+1):
url = "http://weixin.sogou.com/weixin?query=%s&_sug_type_=&s_from=input&_sug_=n&type=%d&page=1&ie=utf8" % (keycode,page)
data = use_proxy(url)
print ("data1的內(nèi)容是",data)
listurl_pattern = '
.*?("http://.*?)
'
result = re.compile(listurl_pattern,re.S).findall(data)
print (result)
if len(result) == 0:
print ("沒有可用的url")
sys.exit()
for i in range(len(result)):
res = result[i].replace("amp;","").split(" ")[0].replace("\"" ,"")
#list_url.append(res) #加入列表
self.urlque.put(res) ##加入隊(duì)列
self.urlque.task_done()
#return list_url
except urllib.error.URLError as e:
if hasattr(e, "code"):
print(e.code)
elif hasattr(e, "reason"):
print(e.reason)
except Exception as e:
print ("exception:",e)
##根據(jù)url獲取文章內(nèi)容
class get_url_content(threading.Thread):
def __init__(self,urlque):
threading.Thread.__init__(self)
self.urlque = urlque
def run(self):
fh1 = open("D:\\python-script\\1.html", 'wb')
html1 = '''\n\n\n
\n
微信文章
\n'''
fh1.write(html1.encode("utf-8"))
fh1.close()
fh = open("D:\\python-script\\1.html", 'ab')
while True:
try:
url = self.urlque.get()
data_content = use_proxy(url)
title_pattern = '
.*?'
result_title = re.compile(title_pattern, re.S).findall(data_content)
##標(biāo)題
res_title = result_title[0].replace("
", "").replace("
","").strip()
content_pattern = 'id="js_content">(.*?)
'
content = re.compile(content_pattern, re.S).findall(data_content)
#c = '
'
# for i in content:
# ##內(nèi)容
# c_content=i.replace(c, "").replace("
", "").replace("
", "")
fh.write(res_title.encode("utf-8"))
for i in content:
fh.write(i.strip().encode("utf-8"))
except UnicodeEncodeError as e:
continue
fh.close()
class contrl(threading.Thread):
def __init__(self,urlqueue):
threading.Thread.__init__(self)
self.urlqueue = urlqueue
while True:
print ("程序正在執(zhí)行")
if self.urlqueue.empty():
time.sleep(3)
print ("程序執(zhí)行完畢")
exit()
if __name__ == '__main__':
pagestart = 1
pageend = 2
key = "人工智能"
get_url = get_url(key,pagestart,pageend,urlque)
get_url.start()
get_content = get_url_content(urlque)
get_content.start()
cntrol = contrl(urlque)
cntrol.start()
更多關(guān)于Python相關(guān)內(nèi)容可查看本站專題:《Python Socket編程技巧總結(jié)》、《Python正則表達(dá)式用法總結(jié)》、《Python數(shù)據(jù)結(jié)構(gòu)與算法教程》、《Python函數(shù)使用技巧總結(jié)》、《Python字符串操作技巧匯總》、《Python入門與進(jìn)階經(jīng)典教程》及《Python文件與目錄操作技巧匯總》
希望本文所述對(duì)大家Python程序設(shè)計(jì)有所幫助。
更多文章、技術(shù)交流、商務(wù)合作、聯(lián)系博主
微信掃碼或搜索:z360901061
微信掃一掃加我為好友
QQ號(hào)聯(lián)系: 360901061
您的支持是博主寫作最大的動(dòng)力,如果您喜歡我的文章,感覺我的文章對(duì)您有幫助,請(qǐng)用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧,狠狠點(diǎn)擊下面給點(diǎn)支持吧,站長(zhǎng)非常感激您!手機(jī)微信長(zhǎng)按不能支付解決辦法:請(qǐng)將微信支付二維碼保存到相冊(cè),切換到微信,然后點(diǎn)擊微信右上角掃一掃功能,選擇支付二維碼完成支付。
【本文對(duì)您有幫助就好】元

