pep8优化代码风格

shaojava · Mar 1, 2017 · a41a8a3 · a41a8a3
1 parent 99707cf
commit a41a8a3
Show file tree

Hide file tree

Showing 10 changed files with 57,866 additions and 126 deletions.
diff --git a/10.selenium/BAIDU/selenium_so_chrome.py b/10.selenium/BAIDU/selenium_so_chrome.py
@@ -10,40 +10,43 @@
 #   功能：结合crontab定时启动每天自动登录so网站,刷银牌用
 #-------------------------------------------------------------------------
 
+import sys
+import time
+
 from selenium import webdriver
 from selenium.webdriver.common.keys import Keys
-import time,sys
 
 # 中文编码设置
 reload(sys)
 sys.setdefaultencoding('utf-8')
 Type = sys.getfilesystemencoding()
 
-#加载内核
+# 加载内核
 #driver = webdriver.PhantomJS()
 driver = webdriver.Chrome()
-#发起请求
+# 发起请求
 print 'beging_0'
-#driver.get("http://lbsyun.baidu.com/skins/MySkin/resources/iframs/heightAccApi.html")
-#driver.get("https://s.m.taobao.com/h5?event_submit_do_new_search_auction=1&_input_charset=utf-8&topSearch=1&atype=b&searchfrom=1&action=home%3Aredirect_app_action&from=1&sst=1&n=20&buying=buyitnow&q=%E7%9A%AE%E8%A3%A4%E5%A5%B3")
+# driver.get("http://lbsyun.baidu.com/skins/MySkin/resources/iframs/heightAccApi.html")
+# driver.get("https://s.m.taobao.com/h5?event_submit_do_new_search_auction=1&_input_charset=utf-8&topSearch=1&atype=b&searchfrom=1&action=home%3Aredirect_app_action&from=1&sst=1&n=20&buying=buyitnow&q=%E7%9A%AE%E8%A3%A4%E5%A5%B3")
 driver.get("https://h5.m.taobao.com/awp/core/detail.htm?id=538287375253&abtest=25&rn=51380cce73c6e338c4f512e1d592ddb7&sid=a706d7e5bb79cfe64053bad190a02f4c")
 # http://lbsyun.baidu.com/index.php?title=webapi/high-acc-ip
 
-#获取用户名框并输入
+# 获取用户名框并输入
 print 'beging_1'
 #elem = driver.find_element_by_xpath('/html/body/table/tbody/tr[1]/td[2]/input')
 
-#elem.send_keys("171.15.132.58")
+# elem.send_keys("171.15.132.58")
 
-#获取密码框并输入
-#print 'beging_2'
-elem = driver.find_element_by_xpath('//*[@class="desc_page_box normal"]').click()
-#elem.send_keys("**")desc_page_box normal
-#通过回车键进行登录
-#print 'beging_3'
-#elem.send_keys(Keys.RETURN)
+# 获取密码框并输入
+# print 'beging_2'
+elem = driver.find_element_by_xpath(
+    '//*[@class="desc_page_box normal"]').click()
+# elem.send_keys("**")desc_page_box normal
+# 通过回车键进行登录
+# print 'beging_3'
+# elem.send_keys(Keys.RETURN)
 
-#time.sleep(10)
+# time.sleep(10)
 js1 = 'return document.body.scrollHeight'
 js2 = 'window.scrollTo(0, document.body.scrollHeight)'
 
@@ -52,20 +55,20 @@
     old_scroll_height = driver.execute_script(js1)
     driver.execute_script(js2)
     time.sleep(3)
-    name = ''+time.ctime().replace(' ','-')+'.png'
+    name = '' + time.ctime().replace(' ', '-') + '.png'
     driver.save_screenshot(name)
-#保存页面截图和源码
-name = ''+time.ctime().replace(' ','-')+'.png'
+# 保存页面截图和源码
+name = '' + time.ctime().replace(' ', '-') + '.png'
 driver.save_screenshot(name)
 #f = open(name_html.encode('utf-8'),'w')
-#f.write(driver.page_source)
-#f.close()
+# f.write(driver.page_source)
+# f.close()
 
-#print driver.page_source.encode('utf8')
+# print driver.page_source.encode('utf8')
 
 time.sleep(5)
 
-#driver.quit()
-#elem.clear()
-#time.sleep(10)
+# driver.quit()
+# elem.clear()
+# time.sleep(10)
 driver.close()
diff --git a/10.selenium/as-rank/selenium_so_phamtomjs.py b/10.selenium/as-rank/selenium_so_phamtomjs.py
@@ -10,37 +10,40 @@
 #   功能：结合crontab定时启动每天自动登录so网站,刷银牌用
 #-------------------------------------------------------------------------
 
+import sys
+import time
+
 from selenium import webdriver
 from selenium.webdriver.common.keys import Keys
-import time,sys
 
 # 中文编码设置
 reload(sys)
 sys.setdefaultencoding('utf-8')
 Type = sys.getfilesystemencoding()
 
-#加载内核
+# 加载内核
 driver = webdriver.PhantomJS()
 
-#发起请求≈
-for i in range(10,20):
+# 发起请求≈
+for i in range(10, 20):
     try:
-        print i,'begin',time.ctime()
+        print i, 'begin', time.ctime()
         num = i
-        url = 'http://as-rank.caida.org/?mode0=as-info&mode1=as-table&as='+str(num)+'&data-selected-id=39'
+        url = 'http://as-rank.caida.org/?mode0=as-info&mode1=as-table&as=' + \
+            str(num) + '&data-selected-id=39'
         driver.implicitly_wait(10)
         driver.get(url)
-        #保存页面截图和源码
-        name = './png/'+str(num)+'.png'
-        name_html = "./code/"+str(num)+'.html'
+        # 保存页面截图和源码
+        name = './png/' + str(num) + '.png'
+        name_html = "./code/" + str(num) + '.html'
 
         driver.save_screenshot(name)
-        f = open(name_html,'w')
+        f = open(name_html, 'w')
         f.write(driver.page_source)
         f.close()
 
-        #time.sleep(5)
-        print i,'end  ',time.ctime()
-    except Exception,e:
+        # time.sleep(5)
+        print i, 'end  ', time.ctime()
+    except Exception, e:
         print e
 driver.close()
diff --git a/6.爬虫项目源码/1.优酷网/read_useragent_txt_forge.py b/6.爬虫项目源码/1.优酷网/read_useragent_txt_forge.py
@@ -11,53 +11,57 @@
 #         读取一个随机的头部User-Agent 信息 添加到请求中此作为基础的伪造,
 #
 #-------------------------------------------------------------------------
-import requests
 import random
 import re
 
-#发起请求,
-def get_request(url,user_agent):
-	'''参数引入及头信息'''
-	if len(user_agent ) < 10:
-		user_agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:39.0) Gecko/20100101 Firefox/39.0'
-	#此处修改头字段,
-	headers = {
-    	'Host':"v.youku.com",
-    	"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
-    	"Accept-Encoding": "gzip, deflate, sdch",
-    	"Accept-Language": "zh-CN,zh;q=0.8",
-		'Cache-Control':'no-cache',
-    	"Connection": "keep-alive",
-    	"User-Agent": user_agent,
-		'Referer':'http://www.youku.com/'
-	}
-	try:
-		html=requests.get(url,headers=headers, timeout=20).text
-		#print html
-		return html
-	except Exception,e:
-		print Exception,e
-		return -1
+import requests
+
+
+# 发起请求,
+
+
+def get_request(url, user_agent):
+    '''参数引入及头信息'''
+    if len(user_agent) < 10:
+        user_agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:39.0) Gecko/20100101 Firefox/39.0'
+    # 此处修改头字段,
+    headers = {
+        'Host': "v.youku.com",
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+        "Accept-Encoding": "gzip, deflate, sdch",
+        "Accept-Language": "zh-CN,zh;q=0.8",
+        'Cache-Control': 'no-cache',
+        "Connection": "keep-alive",
+        "User-Agent": user_agent,
+        'Referer': 'http://www.youku.com/'
+    }
+    try:
+        html = requests.get(url, headers=headers, timeout=20).text
+        # print html
+        return html
+    except Exception, e:
+        print Exception, e
+        return -1
 
 if __name__ == '__main__':
-	#此url为任意一个具有某视频播放窗口的页面
-	url = "http://v.youku.com/v_show/id_XMTgzNDI0MjkzNg==.html?from=y1.3-movie-grid-1095-9921.86985-107667.1-1&spm=a2hmv.20009921.yk-slide-107667.5~5~5~5!2~A#paction"
+    # 此url为任意一个具有某视频播放窗口的页面
+    url = "http://v.youku.com/v_show/id_XMTgzNDI0MjkzNg==.html?from=y1.3-movie-grid-1095-9921.86985-107667.1-1&spm=a2hmv.20009921.yk-slide-107667.5~5~5~5!2~A#paction"
 
-	#导入数据集并随机获取一个User-Agent
-	user_agent_list = []
-	f = open('user_agent.txt','r')
-	for date_line in f:
-		user_agent_list.append(date_line.replace('\r\n',''))
-	user_agent = random.choice(user_agent_list)
+    # 导入数据集并随机获取一个User-Agent
+    user_agent_list = []
+    f = open('user_agent.txt', 'r')
+    for date_line in f:
+        user_agent_list.append(date_line.replace('\r\n', ''))
+    user_agent = random.choice(user_agent_list)
 
-	#发起请求
-	html_body = get_request(url,user_agent)
-	print re.findall('http://player.youku.com/player.php/sid/[A-Za-z0-9=]*/v.swf',html_body)
+    # 发起请求
+    html_body = get_request(url, user_agent)
+    print re.findall('http://player.youku.com/player.php/sid/[A-Za-z0-9=]*/v.swf', html_body)
 
 
 #-------------------测试结果-------------------------------
 # 将此链接放在浏览器中可以直接播放,虽然有广告....至于别的数据太简单那就不抓了.
 #[
-#u'http://player.youku.com/player.php/sid/XMTgzNDI0MjkzNg==/v.swf',
-#u'http://player.youku.com/player.php/sid/XMTgzNDI0MjkzNg==/v.swf'
+# u'http://player.youku.com/player.php/sid/XMTgzNDI0MjkzNg==/v.swf',
+# u'http://player.youku.com/player.php/sid/XMTgzNDI0MjkzNg==/v.swf'
 #]
diff --git a/6.爬虫项目源码/10.百度百科大学/get_url.py b/6.爬虫项目源码/10.百度百科大学/get_url.py
@@ -1,8 +1,9 @@
-#coding:utf-8
-import requests
+# coding:utf-8
 import sys
 
-#中文编码设置
+import requests
+
+# 中文编码设置
 reload(sys)
 sys.setdefaultencoding('utf-8')
 Type = sys.getfilesystemencoding()
@@ -25,14 +26,14 @@
     'user-agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36",
     'x-requested-with': "XMLHttpRequest",
     'postman-token': "36f249ee-4f92-4669-7491-274692665478"
-    }
+}
 print 'a = ['
 for i in range(84):
     payload_now = payload % i
     response = requests.request("POST", url, data=payload_now, headers=headers)
     dic = eval(response.content.decode('utf8').encode('utf8'))
     dic1 = dic['lemmaList']
     for i in dic1:
-        #print i['lemmaTitle'].decode('utf8').encode('utf8')
-        print '"'+i['lemmaUrl']+'",'
+        # print i['lemmaTitle'].decode('utf8').encode('utf8')
+        print '"' + i['lemmaUrl'] + '",'
 print ']'