xpath-grab english name
from scrapy.spider import Spider
from scrapy.crawler import CrawlerProcess import pymysql conn = pymysql.connect(
host='localhost',
user='root',
passwd='root',
charset='utf8',
database='bak',
use_unicode=False
)
cursor = conn.cursor() class EnglishName(Spider):
name = 'EnglishName'
start_urls = ['http://www.world-english.org/boys_names%(wlist)s.htm' % {'wlist': wlist} for wlist in
['_list', '-d-f', '-d-f', '-g-i.', '-j-l','-m-o', '-p-r', '-s-u.', '-v-z']] def parse(self, response):
w = 0
for wname in response.xpath(".//table[@width='92%']//font[@face='Verdana']/text()").extract():
if w==0 :
w=1
grab_url = response.url
isboy = 1
sql = 'insert into namelist (grab_url,isboy,given_name) values ("%s",%i,"%s")'
print sql % (grab_url, isboy, wname)
try:
cursor.execute(sql % (grab_url, isboy, wname))
conn.commit()
except Exception, e:
print e
conn.rollback()
if w==1:
w = 0
print wname if __name__ == '__main__':
process = CrawlerProcess({'DOWNLOAD_DELAY': 2,
'CONCURRENT_REQUESTS_PER_DOMAIN': 6,
'USER_AGENT': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2950.5 Safari/537.36'
})
process.crawl(EnglishName)
process.start()
CODE <html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=windows-1250">
<meta name="GENERATOR" content="Microsoft FrontPage 12.0">
<meta name="ProgId" content="FrontPage.Editor.Document">
<title>List of English Names and their Meaning - Boys J - L</title>
</head> <body> <table cellSpacing="0" cellPadding="0" width="730" align="center" border="0">
<tbody>
<tr>
<td vAlign="bottom" align="left" width="316">
<p><a href="http://www.world-english.org"><img height="50" src="world-englishWORD.jpg" width="285" border="0"></a></p>
</td>
<td vAlign="bottom" align="middle" width="322">
<p style="MARGIN-BOTTOM: 6px"><b><font face="Verdana" color="#000000">The
one-stop resource for the English language and more ...</font></b></p>
</td>
<td vAlign="bottom" align="middle" width="86"><font size="1">®<img height="43" src="world_english_global.gif" width="46" border="0"></font></td>
</tr>
</tbody>
</table>
<table cellSpacing="0" cellPadding="0" width="729" align="center" bgColor="#ffffff" border="0">
<tbody>
<tr align="middle">
<td width="727" colSpan="7">
<hr noShade SIZE="1">
</td>
</tr>
<tr class="text-body2" vAlign="bottom" align="middle">
<td class="nav_top" align="middle" width="73"><font face="Verdana" color="#0000ff" size="2"><a href="http://www.world-english.org">Home</a></font></td>
<td align="middle" width="189"><font face="Verdana" size="2"><a href="http://www.world-english.org/services.htm">Language
Services</a></font></td>
<td align="middle" width="145"><font face="Verdana" size="2"><a href="http://www.world-english.org/onlineschool.htm">Online
School</a></font></td>
<td align="middle" width="191"><font face="Verdana" size="2"><a href="http://www.world-english.org/english_newsletter.htm">English
Newsletter</a></font></td>
<td align="middle" width="83"><font face="Verdana" size="2"><a href="http://www.world-english.org/search.htm">Search</a></font></td>
<td align="middle" width="140"><font face="Verdana" size="2"><a href="http://www.world-english.org/tell.htm">Tell
A Friend</a></font></td>
<td align="middle" width="70"><font face="Verdana" size="2"><a href="kontakt.htm">Contact</a></font></td>
</tr>
</tbody>
</table>
<table cellSpacing="0" cellPadding="0" width="728" align="center" bgColor="#ffffff" border="0">
<tbody>
<tr align="middle">
<td width="726">
<hr align="right" width="100%" noShade SIZE="1">
<p align="left"> </p>
<h1 align="center"><font color="#0000ff" size="5" face="Verdana"><b>THE
MEANING OF ENGLISH NAMES</b></font></h1>
<h2 align="center"><font face="Verdana" size="4">What do English Boys' Names
Mean?</font></h2>
<p align="center"><font face="Verdana" size="2">Here is fairly
comprehensive list of first (Christian) names used in the
English-speaking world (Great Britain, the United States, Ireland;
Australia etc.). It also includes an indication of the traditional
meaning of these names. It should of some use to anyone thinking about
choosing a name for a baby or interested in finding out what their own
name means.</font>
<p align="center"><font face="Verdana" size="2"><a href="boys_names.htm">Top
10 English names</a></font>
<p align="center"><font face="Verdana" size="2"><a href="boys_names_list.htm">A - C</a> /
<a href="boys_names-g-i.htm">D - F</a> / <a href="http://www.world-english.org/boys_names-g-i.htm">G - I</a> / J - L /
<a href="boys_names-m-o.htm">M - O</a>
/ <a href="http://www.world-english.org/boys_names-p-r.htm">P - R</a> /
<a href="http://www.world-english.org/boys_names-s-u.htm">S - U</a> /
<a href="http://www.world-english.org/boys_names-v-z.htm">V - Z</a></font>
<p align="center">
<div align="center">
<table cellPadding="0" width="92%" border="1">
<tbody>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jack</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Godly</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jacob</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Conqueror</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">James,
Jimmy</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Supplanter</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jarvis</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Accurate
Arrow</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jason</font></td>
<td vAlign="top" align="middle"><font face="Verdana">God is my
Saviour</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jasper</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Bearer of
Treasure</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jed</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Beloved of
the Lord</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jeffrey</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Peace
Bringer</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jeremiah,
Jeremy</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Exalted</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jerome</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Of Sacred
Name</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jesse</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Gift Giver</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">John</font></td>
<td vAlign="top" align="middle"><font face="Verdana">God is
Gracious</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Jonathan</font></td>
<td vAlign="top" align="middle"><font face="Verdana">A Gift</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Joseph,
Joey, Joe</font></td>
<td vAlign="top" align="middle"><font face="Verdana">God
Multiplies</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Joshua</font></td>
<td vAlign="top" align="middle"><font face="Verdana">God is my
Salvation</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Justin</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Just</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kane</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Honor</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Keene</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Sharp</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Keegan</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Fiery</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Keaton</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Where Hawks
Go</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Keith</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Forest</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kelsey</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Island of
Ships</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kelvin</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Friend of the Sea</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kendall</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Narrow River</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kendrick</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Ruler</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kenneth,
Ken</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Handsome</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kent</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Bright
White</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kenway</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Courageous
in Battle</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kenyon</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Blonde
Haired</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kerry</font></td>
<td vAlign="top" align="middle"><font face="Verdana">The Dark</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kerwin</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Dark
Skinned</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kevin</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Handsome</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kiefer</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Barrel
Maker</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kilby</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Residence
Name</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kilian</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Blind</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kim</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Chief</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kimball</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Royally
Brave</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kingsley</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Residence
Name</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kirby</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Residence
Name</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kirk</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Church</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kit</font></td>
<td vAlign="top" align="middle"><font face="Verdana">The
Christ-Bearer</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kody</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Helpful</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Konrad</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Bold
Speaker</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kurt</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Able in
Counsel</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Kyle</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Handsome</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lambert</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Land Bright</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lamont</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Lawyer</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lancelot</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Land</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Landon</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Owner</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Landry</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Ruler of
the Place</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lane</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Narrow Road</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lars</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Variant of
Lawrence</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Laurence</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Bay or
Laurel Tree</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lee</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Meadow</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Leith</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Wide</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Leonard,
Leo, Leon</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Bold Lion</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Leroy</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Powerful
King</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Leslie</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Residence
Name</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lester</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Camp of the
Legion</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lincoln</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Residence
Name</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lionel</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Lion-like</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lloyd</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Grey</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Logan</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Trench or
Forest</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lombard</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Long-Beard</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Louis,
Lewis</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Warrior</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lowell</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Beloved</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lucas, Luke</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Luminous</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Luther</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Warrior</font></td>
</tr>
<tr>
<td vAlign="top" align="middle"><font face="Verdana">Lyndon</font></td>
<td vAlign="top" align="middle"><font face="Verdana">Linden Tree</font></td>
</tr>
</tbody>
</table>
</div>
<p style="MARGIN-BOTTOM: -20px" align="center"> </p>
<p style="MARGIN-BOTTOM: -20px" align="center"><font size="2">COPYRIGHT </font>
© <font face="Courier New"><b>world-english.org</b> </font><font face="Arial"> </font>
<font size="2">1999-2004 <b>ALL RIGHTS
RESERVED</b></font></p>
<p style="MARGIN-BOTTOM: -20px" align="center"> </p>
<p style="MARGIN-BOTTOM: -18px" align="center"> </p>
<table cellSpacing="0" cellPadding="0" width="100%" border="0">
<tbody>
<tr>
<td>
<p align="center"><font face="Courier New"><small style="COLOR: #999999"><a href="http://world-english.org/about.htm"><font size="2">About
Us</font></a><font size="2"> | <a href="http://www.world-english.org/search.htm">Search
Our Site</a> | </font></small><font size="2"><a href="http://www.world-english.org/tell.htm">Tell
A Friend</a> <small style="COLOR: #999999">| </small><a href="kontakt.htm">e-mail
us</a></font></font></p>
</td>
</tr>
</tbody>
</table>
<p align="center"> <script type="text/javascript"><!--
google_ad_client = "pub-6321590226208373";
google_ad_width = 728;
google_ad_height = 90;
google_ad_format = "728x90_as";
//--></script>
<script type="text/javascript"
src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script></p>
<p align="center"> </p> </body>
http://www.world-english.org/boys_names-j-l.htm
w
from scrapy.spider import Spider
from scrapy.crawler import CrawlerProcess import pymysql conn = pymysql.connect(
host='localhost',
user='root',
passwd='root',
charset='utf8',
database='bak',
use_unicode=False
)
cursor = conn.cursor() class EnglishName(Spider):
name = 'EnglishName'
start_urls = ['http://ename.dict.cn/list/%(wisboy)s/%(az)s/%(page)i' % {'wisboy': wisboy, 'az': az,
'page': page, } for wisboy in
['male', 'female'] for az in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
for page in range(1, 80, 1)] def parse(self, response): for wname in response.xpath(".//em[@class='male']/../preceding-sibling::td[1]/a/text()").extract():
grab_url = response.url
isboy = 1
sql = 'insert into namelist (grab_url,isboy,given_name) values ("%s",%i,"%s")'
print sql % (grab_url, isboy, wname)
try:
cursor.execute(sql % (grab_url, isboy, wname))
conn.commit()
except Exception, e:
print e
conn.rollback() if __name__ == '__main__':
process = CrawlerProcess({'DOWNLOAD_DELAY': 2,
'CONCURRENT_REQUESTS_PER_DOMAIN': 6,
'USER_AGENT': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2950.5 Safari/537.36'
})
process.crawl(EnglishName)
process.start()
http://ename.dict.cn/list/male/F/4
CODE <!DOCTYPE HTML>
<html>
<head>
<meta name="renderer" content="webkit">
<meta http-equiv="X-UA-Compatible" content="IE=EmulateIE7"/>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
<title>字母检索F列表_男性英文名_人名词典 - Dict.CN 海词</title> <meta name="keywords" content="男性英文名,英文名"/>
<meta name="description" content="英文名人名词典提供男性英文名，字母检索F列表，男性英文名大全，更多男性英文名，字母检索F列表，男性英文名大全，星座英文名以及他们的读音到海词网。"/>
<meta name="author" content="海词词典"/>
<link rel="canonical" href="http://ename.dict.cn/list/male/F"/>
<link rel="icon" href="http://dict.cn/favicon.ico" type="/image/x-icon"/>
<link rel="shortcut icon" href="http://dict.cn/favicon.ico" type="/image/x-icon"/>
<link href="http://i1.haidii.com/v/1484140449/i1/css/base.min.css" rel="stylesheet" type="text/css"/>
<link href="http://i1.haidii.com/v/1484140452/i1/css/obase.min.css" rel="stylesheet" type="text/css"/>
<script>var cur_dict = 'ename';
var i1_home = 'http://i1.haidii.com';
var xuehai_home = 'http://xuehai.cn';
var passport_home = 'http://passport.dict.cn';</script>
<script type="text/javascript" src="http://i1.haidii.com/v/1408420485/i1/js/jquery-1.8.0.min.js"></script> <script>var crumb = '', dict_homepath = 'http://dict.cn', hc_jspath = 'http://i1.haidii.com/v/1484140447/i1/js/hc3/hc.min.js', use_bingTrans = '', multi_langs = '';</script>
</head>
<body>
<object style="position:absolute;top:-1000%;width:1px;height:1px;opacity:0;filter:progid:DXImageTransform.Microsoft.Alpha(opacity=0);"
width="1" height="1" id="daudio" type="application/x-shockwave-flash" data="http://dict.cn/player/player.swf">
<param name="movie" value="http://dict.cn/player/player.swf">
<param name="quality" value="high"/>
<param name="bgcolor" value="#ffffff"/>
<param name="allowScriptAccess" value="always"/>
<param name="allowFullScreen" value="true"/>
<param name="hasPriority" value="true"/>
<param name="FlashVars" value="volume=100"/>
<embed style="position:absolute;top:-1000%;width:1px;height:1px;-khtml-opacity:0;-moz-opacity:0;opacity:0;"
src="http://dict.cn/player/player.swf" allowscriptaccess="always" allowfullscreen="true" quality="high"
type="application/x-shockwave-flash" pluginspage="http://www.macromedia.com/go/getflashplayer"></embed>
</object>
<div id="header">
<div class="nav">
<div class="links">
<a class=cur href="http://dict.cn">海词</a>
<a onclick="cnewClose(this);" href="http://cidian.dict.cn/center.html?iref=dict-header-center">权威词典</a> <div id="cnewDiv" style="position: relative;float:left;line-height: 40px;height:40px;">
<div style="position: absolute;top:-10px;left:-23px;"><img style="vertical-align: middle"
src="http://i1.haidii.com/v/1420610131/i1/cidian/images/new.png"/>
</div>
</div>
<script>function cnewClose(obj) {
var Days = 3600;
var exp = new Date();
exp.setTime(exp.getTime() + Days * 24 * 60 * 60 * 1000);
document.cookie = 'cnew' + "=" + escape(1) + ";expires=" + exp.toGMTString() + ";path=/;domain=.dict.cn";
document.cookie = 'cnewt' + "=" + escape(1420560000) + ";expires=" + exp.toGMTString() + "path=/;domain=.dict.cn";
$("#cnewDiv").hide();
}</script>
<a href="http://fanyi.dict.cn">翻译</a>
<style type="text/css">#header .links .top-download a {
width: 140px;
height: 40px;
line-height: normal;
background: url(http://i1.haidii.com/v/1408420472/i1/images/top-download-icon2.png) 0 0 no-repeat
} #header .links .top-download a:hover {
background: url(http://i1.haidii.com/v/1408420472/i1/images/top-download-icon2.png) 0 -40px no-repeat
}</style>
<div class="top-download"><a href="http://cidian.dict.cn/home.html?iref=dict-header-button"></a></div>
</div>
<div class="login">
<em action="feedback" onclick="feedBackForm(this);" title="意见反馈">意见反馈</em>
<i>|</i>
<a title="注册" href="http://passport.dict.cn/register">注册</a><i>|</i><a title="登录"
href="http://passport.dict.cn/login">登录</a>
</div>
</div>
<script>var pagetype = '';</script>
<script type='text/javascript'>
var googletag = googletag || {};
googletag.cmd = googletag.cmd || [];
(function () {
var gads = document.createElement('script');
gads.async = true;
gads.type = 'text/javascript';
var useSSL = 'https:' == document.location.protocol;
gads.src = (useSSL ? 'https:' : 'http:') +
'//www.googletagservices.com/tag/js/gpt.js';
var node = document.getElementsByTagName('script')[0];
node.parentNode.insertBefore(gads, node);
})();
</script> <script type='text/javascript'>
googletag.cmd.push(function () {
googletag.defineSlot('/146434140/search_tab', [200, 48], 'div-gpt-ad-1422600134018-10').addService(googletag.pubads());
googletag.pubads().enableSingleRequest();
googletag.enableServices();
});
</script>
<div class="top">
<a href="/" class="logo"><img alt="海词词典" titile="海词词典"
src="http://i1.haidii.com/v/1408420472/i1/images/ename_search_logo.png"/></a> <div class="search">
<div class="search_nav">
<a href="http://dict.cn" data-param="zh,en,other"><b>英 汉</b></a>
<a href="http://dict.cn/kr/" data-param="zh,en,other"><b>韩 汉</b></a> <a href="http://dict.cn/jp/" data-param="zh,en,other"><b>日 汉</b></a> <a
class="sbox_morebtn searchnav-morea" href="javascript:;">更多</a> <em>|</em>
<a href="http://juhai.dict.cn" data-param="zh,en">句海</a>
<a href="http://hanyu.dict.cn" data-param="zh">汉语</a>
<em>|</em>
<a href="http://shh.dict.cn" data-param="zh">上海话</a>
<a href="http://gdh.dict.cn" data-param="zh">广东话</a>
<a href="http://abbr.dict.cn" data-param="zh,en">缩略语</a>
<a href="http://ename.dict.cn" data-param="zh,en">人名</a>
</div>
<div class="sbox_more_wrap">
<div class="sbox_more">
<div class="sbox_marrow"></div>
<div class="sbox_mlangs">
<a style="display:none" href="http://dict.cn/jp/" data-param="zh,en,other"><b>日 汉</b></a>
<a href="http://dict.cn/fr/" data-param="zh,en,other"><b>法 汉</b></a>
<a href="http://dict.cn/de/" data-param="zh,en,other"><b>德 汉</b></a>
<a href="http://dict.cn/es/" data-param="zh,en,other"><b>西 汉</b></a>
<a href="http://dict.cn/it/" data-param="zh,en,other"><b>意 汉</b></a>
<a href="http://dict.cn/ru/" data-param="zh,en,other"><b>俄 汉</b></a>
</div>
</div>
</div> <div class="search_box">
<form action="http://ename.dict.cn/search.php" method="get">
<input type="text" id="q" class="search_input" name="q" value="" autocomplete="off"
placeholder="请输入英/汉字词句" x-webkit-speech><input type="submit" class="search_submit"
id="search" title="查词" value="">
</form>
</div>
</div>
<div class="spread" style="padding-left:10px;">
<!-- search_tab -->
<div id='div-gpt-ad-1456898554209-4' style='width:200px; height:48px;'>
<script type='text/javascript'>
googletag.cmd.push(function () {
googletag.display('div-gpt-ad-1456898554209-4');
});
</script>
</div> </div>
</div>
</div>
<script type='text/javascript'>
var googletag = googletag || {};
googletag.cmd = googletag.cmd || [];
(function () {
var gads = document.createElement('script');
gads.async = true;
gads.type = 'text/javascript';
var useSSL = 'https:' == document.location.protocol;
gads.src = (useSSL ? 'https:' : 'http:') +
'//www.googletagservices.com/tag/js/gpt.js';
var node = document.getElementsByTagName('script')[0];
node.parentNode.insertBefore(gads, node);
})();
</script> <script type='text/javascript'>
googletag.cmd.push(function () {
googletag.defineSlot('/146434140/ename_topbanner', [[728, 90], [970, 90], [1000, 90]], 'div-gpt-ad-1422601564072-0').addService(googletag.pubads());
googletag.defineSlot('/146434140/ename_dbanner', [728, 90], 'div-gpt-ad-1422601564072-1').addService(googletag.pubads());
googletag.pubads().enableSingleRequest();
googletag.enableServices();
});
</script>
<div id="main">
<div style="width:1000px;margin:0 auto;margin-bottom:10px;text-align: center;">
<!-- ename_topbanner -->
<div id='div-gpt-ad-1422601564072-0'>
<script type='text/javascript'>
googletag.cmd.push(function () {
googletag.display('div-gpt-ad-1422601564072-0');
});
</script>
</div>
</div>
<div class="o_mslide">
<div class="obox bx obox-ename">
<div class="obox-t">英文名选择</div>
<div class="obox-c ename_choose">
<ul>
<li><a href="/list/all">全部英文名</a></li>
<li><a href="/list/female">女性英文名</a></li>
<li><a href="/list/male" class="cur">男性英文名</a></li>
<li><a href="/list/neutral">中性英文名</a></li>
<li><a href="/list/celebrity">名人英文名</a></li>
</ul>
</div>
<div class="obox-t">英文名读音</div>
<div class="obox-c ename_read">
<ul>
<li>
<a href="/Hilda" title="查看详细">Hilda</a>希尔达<em class="sound" audio="n2zNza3"></em>
</li>
<li>
<a href="/Hildegarde" title="查看详细">Hildegarde</a>希尔德加德<em class="sound" audio="n1zbzag"></em>
</li>
<li>
<a href="/Hill" title="查看详细">Hill</a>希尔<em class="sound" audio="n0zazaD"></em>
</li>
<li>
<a href="/Hillary" title="查看详细">Hillary</a>希拉里<em class="sound" audio="nAzvzam"></em>
</li>
<li>
<a href="/Hilliard" title="查看详细">Hilliard</a>希利亚德<em class="sound" audio="nAzKzaw"></em>
</li>
<li>
<a href="/Hillman" title="查看详细">Hillman</a>希尔曼<em class="sound" audio="nBzAzaz"></em>
</li>
<li>
<a href="/Hills" title="查看详细">Hills</a>希尔斯<em class="sound" audio="nCz2za2"></em>
</li>
<li>
<a href="/Hilton" title="查看详细">Hilton</a>希尔顿<em class="sound" audio="nDzuzaN"></em>
</li>
<li>
<a href="/Hinds" title="查看详细">Hinds</a>海因兹<em class="sound" audio="nDzKzac"></em>
</li>
<li>
<a href="/Hines" title="查看详细">Hines</a>海因斯<em class="sound" audio="nEzczaH"></em>
</li>
</ul>
</div>
</div>
</div>
<div class="o_m">
<div class="o_mlet">
<a href="javascript:;">字母检索</a>
<a href="/list/male/A">A</a>
<a href="/list/male/B">B</a>
<a href="/list/male/C">C</a>
<a href="/list/male/D">D</a>
<a href="/list/male/E">E</a>
<a href="/list/male/F" class="current">F</a>
<a href="/list/male/G">G</a>
<a href="/list/male/H">H</a>
<a href="/list/male/I">I</a>
<a href="/list/male/J">J</a>
<a href="/list/male/K">K</a>
<a href="/list/male/L">L</a>
<a href="/list/male/M">M</a>
<a href="/list/male/N">N</a>
<a href="/list/male/O">O</a>
<a href="/list/male/P">P</a>
<a href="/list/male/Q">Q</a>
<a href="/list/male/R">R</a>
<a href="/list/male/S">S</a>
<a href="/list/male/T">T</a>
<a href="/list/male/U">U</a>
<a href="/list/male/V">V</a>
<a href="/list/male/W">W</a>
<a href="/list/male/X">X</a>
<a href="/list/male/Y">Y</a>
<a href="/list/male/Z">Z</a>
</div>
<div class="o_mc">
<div class="o_mm">
<div class="mbox">
<div class="mbox-t">在男性分类下以字母F开头的英文名：</div>
<div class="mbox-c">
<table class="enname-all">
<tr>
<th>英文名</th>
<th>性别</th>
<th>音标</th>
<th>中文</th>
<th>来源</th>
<th>流行度</th>
</tr>
<tr class="bg">
<td><a href="/Frederick">Frederick</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>['fredrik]</i></td>
<td>弗雷德里克</td>
<td><bdo>古德语</bdo></td>
<td><span class="star3"></span></td>
</tr>
<tr>
<td><a href="/Freeman">Freeman</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>['fri:mən]</i></td>
<td>弗里曼</td>
<td><bdo>古英语</bdo></td>
<td><span class="star4"></span></td>
</tr>
<tr class="bg">
<td><a href="/French">French</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>[frentʃ]</i></td>
<td>弗伦奇</td>
<td><bdo>中世纪英语</bdo></td>
<td><span class="star3"></span></td>
</tr>
<tr>
<td><a href="/Frey">Frey</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>[frei]</i></td>
<td>弗雷</td>
<td><bdo>英语</bdo></td>
<td><span class="star2"></span></td>
</tr>
<tr class="bg">
<td><a href="/Fritz">Fritz</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>[frits]</i></td>
<td>弗里茨</td>
<td><bdo>古德语</bdo></td>
<td><span class="star2"></span></td>
</tr>
<tr>
<td><a href="/Frost">Frost</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>[frɔst]</i></td>
<td>弗罗斯特</td>
<td><bdo>古英语</bdo></td>
<td><span class="star3"></span></td>
</tr>
<tr class="bg">
<td><a href="/Fuller">Fuller</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>[fulə]</i></td>
<td>富勒</td>
<td><bdo>古英语</bdo></td>
<td><span class="star3"></span></td>
</tr>
<tr>
<td><a href="/Fulton">Fulton</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>['fultən]</i></td>
<td>富尔顿</td>
<td><bdo>古英语</bdo></td>
<td><span class="star3"></span></td>
</tr>
<tr class="bg">
<td><a href="/Funk">Funk</a></td>
<td><em class="male" title="男性"></em></td>
<td><i>[fʌŋk]</i></td>
<td>芬克</td>
<td><bdo></bdo></td>
<td><span class="star2"></span></td>
</tr>
</table>
<div class="pager" style="margin-top:15px;">
<a href="/list/male/F/1">最前页</a>
<span>
<a href="/list/male/F/3">上一页</a>
<a href="/list/male/F/1">1</a>
<a href="/list/male/F/2">2</a>
<a href="/list/male/F/3">3</a>
<font color="#FF7800">4</font>
<a href="/list/male/F/4">下一页</a>
</span>
共4/4页 <a href="/list/male/F/4">最后页</a>
</div>
</div>
</div>
<div style="margin-bottom:10px;text-align: center;width:728px;margin:0 auto;">
<!-- ename_dbanner -->
<div id='div-gpt-ad-1422601564072-1' style='width:728px; height:90px;'>
<script type='text/javascript'>
googletag.cmd.push(function () {
googletag.display('div-gpt-ad-1422601564072-1');
});
</script>
</div>
</div>
</div>
<div class="o_mr">
<div class="obox">
<div class="obox-t"><span class="fl">常见缩写</span><span class="obox-tab"><a class="cur"
href="javascript:;">女性</a><a
href="javascript:;">男性</a></span></div>
<div class="obox-c">
<ul class="hotname-person">
<li><a href="/Babbie" title="查看详细">Babbie</a><em>['bæbi]</em><b>巴比</b></li>
<li><a href="/Babette" title="查看详细">Babette</a><em>[bæ'bet]</em><b>巴贝特</b></li>
<li><a href="/Babs" title="查看详细">Babs</a><em>[bæbz]</em><b>巴布丝</b></li>
<li><a href="/Bader" title="查看详细">Bader</a><em>['beidə]</em><b>巴德</b></li>
<li><a href="/Barbara" title="查看详细">Barbara</a><em>['ba:bərə]</em><b>巴巴拉</b></li>
<li><a href="/Barbie" title="查看详细">Barbie</a><em>['ba:bi]</em><b>芭比</b></li>
<li><a href="/Bea" title="查看详细">Bea</a><em>[bi:]</em><b>比</b></li>
<li><a href="/Beatrice" title="查看详细">Beatrice</a><em>['bi:ətris]</em><b>比阿特丽斯</b></li>
<li><a href="/Beatty" title="查看详细">Beatty</a><em>['beti]</em><b>比蒂</b></li>
<li><a href="/Becky" title="查看详细">Becky</a><em>['beki]</em><b>贝基</b></li>
</ul>
<ul class="hotname-person">
<li><a href="/Columbus"
title="查看详细">Columbus</a><em>[kə'lʌmbəəs]</em><b>哥伦布</b></li>
<li><a href="/Conley" title="查看详细">Conley</a><em>['kɔnli]</em><b>康利</b></li>
<li><a href="/Conn" title="查看详细">Conn</a><em>[kɔn]</em><b>康恩</b></li>
<li><a href="/Connell" title="查看详细">Connell</a><em>['kɔnəl]</em><b>康奈尔</b></li>
<li><a href="/Connolly" title="查看详细">Connolly</a><em>['kɔnəli:]</em><b>康诺利</b>
</li>
<li><a href="/Connor" title="查看详细">Connor</a><em>[kɔnə]</em><b>康纳</b></li>
<li><a href="/Conrad" title="查看详细">Conrad</a><em>['kɔnræd]</em><b>康拉德</b></li>
<li><a href="/Conroy" title="查看详细">Conroy</a><em>['kɔnrɔi]</em><b>康罗伊</b></li>
<li><a href="/Conway" title="查看详细">Conway</a><em>['kɔn.wei]</em><b>康威</b></li>
<li><a href="/Corbett" title="查看详细">Corbett</a><em>['kɔ:bət]</em><b>科比特</b></li>
</ul>
</div>
</div>
<div class="obox">
<div class="obox-t">星座英文名</div>
<div class="obox-c">
<p class="constellation">
<a href="/list/%E7%99%BD%E7%BE%8A">白羊座</a>
<a href="/list/%E9%87%91%E7%89%9B">金牛座</a>
<a href="/list/%E5%8F%8C%E5%AD%90">双子座</a>
<a href="/list/%E5%B7%A8%E8%9F%B9">巨蟹座</a>
<a href="/list/%E7%8B%AE%E5%AD%90">狮子座</a>
<a href="/list/%E5%A4%84%E5%A5%B3">处女座</a>
<a href="/list/%E5%A4%A9%E7%A7%A4">天秤座</a>
<a href="/list/%E5%A4%A9%E8%9D%8E">天蝎座</a>
<a href="/list/%E5%B0%84%E6%89%8B">射手座</a>
<a href="/list/%E6%91%A9%E7%BE%AF">摩羯座</a>
<a href="/list/%E6%B0%B4%E7%93%B6">水瓶座</a>
<a href="/list/%E5%8F%8C%E9%B1%BC">双鱼座</a>
</p>
</div>
</div>
</div>
<div class="cl"></div>
</div>
</div>
<div class="cl"></div>
</div>
<div id="footer">
<p><a href="http://about.dict.cn/introduce" ref="nofollow">关于海词</a> - <a
href="http://about.dict.cn/copyrightstatement?cur=1" ref="nofollow">版权声明</a> - <a
href="http://about.dict.cn/contact" ref="nofollow">联系海词</a> - <a target="_blank" href="http://dict.cn/dir/">星级词汇</a>
- <a target="_blank" href="http://dict.cn/dir/ceindex.html">汉字列表</a> - <a target="_blank"
href="http://hr.dict.cn"
ref="nofollow">招贤纳士</a></p> <p>©2003 - 2017 <a href="http://dict.cn/">海词词典</a>(Dict.CN) - 自 2003 年开始服务 <a target="_blank"
href="http://www.miitbeian.gov.cn"
ref="nofollow">沪ICP备08018881号</a> <a
target="_blank"
href="http://www.sgs.gov.cn/lz/licenseLink.do?method=licenceView&entyId=20120601170952752"
style="text-decoration:none;background-color:white;" ref="nofollow"><img border="0"
src="http://i1.haidii.com/i1/images/gs_icon.gif"></a>
<a target="_blank" href="http://www.beian.gov.cn/portal/registerSystemInfo?recordcode=31011502000490"
style="text-decoration:none;background-color:white;" ref="nofollow"><img
src="http://i1.haidii.com/i1/images/beian.png"/><span style="display:none; color:#939393;">沪公网安备 31011502000490号</span></a>
</p> <p style="text-align: center;margin-top:10px;"><a href="http://m.dict.cn" target="_blank">海词词典手机移动站</a></p>
</div>
<script>var langt = '';</script> <script type="text/javascript">
var cur_dict = 'ename', i1_home = 'http://i1.haidii.com', xuehai_home = 'http://xuehai.cn', passport_home = 'http://passport.dict.cn', $dict_id = null, $dict_query = null, $dict_dict = null, $user_id = 0, $dict_ver = 1486623708;
</script>
<script type="text/javascript" src="http://i1.haidii.com/i1/js/ddialog/ddialog.1.0.0.min.js" crossorigin></script>
<script type="text/javascript" src="http://i1.haidii.com/v/1481554274/i1/js/inputPrompt.min.js" crossorigin></script>
<script type="text/javascript" src="http://i1.haidii.com/v/1481554264/i1/js/base.min.js" crossorigin></script>
<div style="display:none;">
<script type="text/javascript">
var _bdhmProtocol = (("https:" == document.location.protocol) ? " https://" : " http://");
document.write(unescape("%3Cscript src='" + _bdhmProtocol + "hm.baidu.com/h.js%3F8fd7837425ffd5a7fb88d32ea7060960' type='text/javascript'%3E%3C/script%3E"));
</script>
</div>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-138041-2']);
_gaq.push(['_setDomainName', 'dict.cn']);
_gaq.push(['_trackPageview']);
(function () {
var ga = document.createElement('script');
ga.type = 'text/javascript';
ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0];
s.parentNode.insertBefore(ga, s);
})();
</script> <script type="text/javascript">
window.onerror = function (errorMsg, url, lineNumber, column, errorObj) {
$.getScript('http://dict-log.cn-hangzhou.log.aliyuncs.com/logstores/jsreport/track?APIVersion=0.6.0&call=error&ver=' + ($dict_ver || '') + '&url=' + encodeURIComponent(url) + '&line=' + lineNumber + '&emsg=' + encodeURIComponent(errorMsg) + '&page=' + _href
+ '&agent=' + encodeURIComponent(navigator.userAgent) + '&column=' + encodeURIComponent(column) + '&StackTrace=' + encodeURIComponent(errorObj));
return true;
};
</script>
</body>
</html>
http://babynames.net/all/starts-with/d?page=2
CODE <div class="main-col">
<div class="names-container">
<div>
<h1>"D" Baby Names</h1>
</div>
<div class="by-letter"><a href="/all/starts-with/a">A</a><a href="/all/starts-with/b">B</a><a
href="/all/starts-with/c">C</a><a href="/all/starts-with/d" class="active">D</a><a
href="/all/starts-with/e">E</a><a href="/all/starts-with/f">F</a><a
href="/all/starts-with/g">G</a><a href="/all/starts-with/h">H</a><a
href="/all/starts-with/i">I</a><a href="/all/starts-with/j">J</a><a
href="/all/starts-with/k">K</a><a href="/all/starts-with/l">L</a><a
href="/all/starts-with/m">M</a><a href="/all/starts-with/n">N</a><a
href="/all/starts-with/o">O</a><a href="/all/starts-with/p">P</a><a
href="/all/starts-with/q">Q</a><a href="/all/starts-with/r">R</a><a
href="/all/starts-with/s">S</a><a href="/all/starts-with/t">T</a><a
href="/all/starts-with/u">U</a><a href="/all/starts-with/v">V</a><a
href="/all/starts-with/w">W</a><a href="/all/starts-with/x">X</a><a
href="/all/starts-with/y">Y</a><a href="/all/starts-with/z">Z</a></div>
<p></p>
<section class="filter-bar">
<div class="input-wrapper">
<input type="checkbox" id="boys" checked="checked" name="boys"/><label
class="checkbox-label checkbox-label-boy" for="boys"><a href="#">Boys</a></label>
</div>
<div class="input-wrapper">
<input type="checkbox" id="girls" checked="checked" name="girls"/><label
class="checkbox-label checkbox-label-girl" for="girls"><a href="#">Girls</a></label>
</div>
<div class="addthis_sharing_toolbox"></div>
</section>
<ul class="names-results listing-view">
<li class="odd">
<a href="/names/dag">
<span class="result-gender boy"></span>
<span class="result-name">Dag</span>
<span class="result-desc">Day</span>
</a>
</li>
<li class="even">
<a href="/names/dagfinn">
<span class="result-gender boy"></span>
<span class="result-name">Dagfinn</span>
<span class="result-desc">Man from Finland, day</span>
</a>
</li>
<li class="odd">
<a href="/names/dagmar">
<span class="result-gender girl"></span>
<span class="result-name">Dagmar</span>
<span class="result-desc">Maid of the day</span>
</a>
</li>
<li class="even">
<a href="/names/dagny">
<span class="result-gender girl"></span>
<span class="result-name">Dagny</span>
<span class="result-desc">New day started</span>
</a>
</li>
<li class="odd">
<a href="/names/dagwood">
<span class="result-gender boy"></span>
<span class="result-name">Dagwood</span>
<span class="result-desc">A shining forest</span>
</a>
</li>
<li class="list-ad" id="list-ad">
<script type='text/javascript'>var width = window.innerWidth || document.documentElement.clientWidth;
if (width <= 767) {
googletag.cmd.push(function () {
googletag.display('list-ad');
});
}</script>
</li>
<li class="even">
<a href="/names/dahlia">
<span class="result-gender girl"></span>
<span class="result-name">Dahlia</span>
<span class="result-desc">Dahlia flower</span>
</a>
</li>
<li class="odd">
<a href="/names/daichi">
<span class="result-gender boy"></span>
<span class="result-name">Daichi</span>
<span class="result-desc">Impressive or grand first son</span>
</a>
</li>
<li class="even">
<a href="/names/daiki">
<span class="result-gender boy"></span>
<span class="result-name">Daiki</span>
<span class="result-desc">Impressive or grand tree</span>
</a>
</li>
<li class="odd">
<a href="/names/daire">
<span class="result-gender boy"></span>
<span class="result-name">Daire</span>
<span class="result-desc">Fertility</span>
</a>
</li>
<li class="even">
<a href="/names/daisuke">
<span class="result-gender boy"></span>
<span class="result-name">Daisuke</span>
<span class="result-desc">Impressive or great help</span>
</a>
</li>
</ul>
</div>
$x(".//div[@class='main-col']")
$x(".//ul[@class='names-results']")
$x(".//ul[@class='names-results listing-view']")
xpath-grab english name的更多相关文章
- scrapy - grab english name
wxpath定位-采集验证-入库-使用. from scrapy.spider import Spider from scrapy.crawler import CrawlerProcess clas ...
- Selenium Xpath Tutorials - Identifying xpath for element with examples to use in selenium
Xpath in selenium is close to must required. XPath is element locator and you need to provide xpath ...
- xpath提取目录下所有标签内的内容，递归 //text（）
利用xpath来提取所有标签里面的内容,即使标签头不同 #-*-coding:utf8-*- import re import os from lxml import etree html = ''' ...
- 安装ipython，使用scrapy shell来验证xpath选择的结果 | How to install iPython and how does it work with Scrapy Shell
1. scrapy shell 是scrapy包的一个很好的交互性工具,目前我使用它主要用于验证xpath选择的结果.安装好了scrapy之后,就能够直接在cmd上操作scrapy shell了. 具 ...
- some phrase for oral english
依我看,在我看来 I suppose that, ... As far as i'm concerned, ... As i see it, ... It seems to me that ... 1 ...
- xpath注入详解
0x01 什么是xpath XPath 即为 XML 路径语言,是 W3C XSLT 标准的主要元素,它是一种用来确定 XML(标准通用标记语言的子集)文档中某部分位置的语言. XPath 基于 ...
- xpath提取多个标签下的text
title: xpath提取多个标签下的text author: 青南 date: 2015-01-17 16:01:07 categories: [Python] tags: [xpath,Pyth ...
- C#+HtmlAgilityPack+XPath带你采集数据(以采集天气数据为例子)
第一次接触HtmlAgilityPack是在5年前,一些意外,让我从技术部门临时调到销售部门,负责建立一些流程和寻找潜在客户,最后在阿里巴巴找到了很多客户信息,非常全面,刚开始是手动复制到Excel, ...
- Lesson 14 Do you speak English?
Text I had an amusing experience last year. After I had left a small village in the south of France. ...
随机推荐
- Ubuntu/Debian下编译PC版的ffmpeg
1.安装git: 在命令行下执行 sudo apt-get install git-core 2.下载最新版本的ffmpeg: git clone git://source.ffmpeg.org/ff ...
- linux和windows动态库加载路径区别
# linux和windows动态库加载路径区别 ### 简介------------------------------ linux加载动态库的路径是系统目录/lib和/usr/lib.- wind ...
- 分享8个常用的jQuery焦点图插件
现在web网页jquery应用越来越广泛,目前几乎每一个WEB项目都在使用jQuery,因为jQuery插件实在太丰富,尤其是一些图片滑块插件和jQuery焦点图插件,更是多如牛毛,很多初学者只需稍微 ...
- php代码检查
最近写php,几个同事都是没写过c的,经常写的变量没有定义,而php没有编译,错误无法发现. 我们现在用的是NetBeans,好在其提供了语法检测,如下图,让编辑器强制显示我错误
- 针对16v554(ttyS0-15)的ttyAT0的ｌｏｇｉｎ配置
1 ## /etc/inittab# console::sysinit:/etc/init.d/rcSconsole::respawn:/sbin/getty -L 115200 ttyAT0 vt1 ...
- httpoxy 漏洞预警及修复方案
影响范围 PHP.Go.Python等开启CGI(Client)模式的脚本语言 Language 环境依赖 HTTP Client PHP php-fpmmod_php Guzzle 4+Artax ...
- 在Asp.net中为图像加入水印信息
using System.Drawing; using System.IO; using System.Drawing.Imaging; private void AddTextToImg(strin ...
- Linux 串口编程
今天对应用层串口编程进行了验证.程序来源于以下参考链接,自己进行了一些注释和更改,记录于此. Tony Liu, 2016-6-17, Shenzhen 参考链接 https://www.ibm.co ...
- 【NLP+Deep learning】好文
http://blog.jobbole.com/77709/ 原文出处: http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/
- MFC 单选按钮Radio使用注意
使用MFC Radio时遇到问题:数据交换时出现断言崩溃框 定位于: 解决方法: 1.按CTRL+D,保证同一组内的radio的tab序号是连续的: 2.同一组内,设置 radio1的属性: gro ...