ó
ç'ÊUc @ s+ d d l Z d d l Z d d l m Z d d l m Z m Z d d l m Z d d l m
Z
d d l m Z m
Z
d d l m Z d d l m Z d e j f d
„ ƒ YZ d e j f d „ ƒ YZ d
e f d „ ƒ YZ d e j f d „ ƒ YZ d e j f d „ ƒ YZ e d k r'e j ƒ n d S( iÿÿÿÿN( t RegexLinkExtractor( t HtmlResponset XmlResponse( t Link( t HtmlParserLinkExtractor( t SgmlLinkExtractort BaseSgmlLinkExtractor( t LxmlLinkExtractor( t get_testdatat LinkExtractorTestCasec B s> e Z d „ Z d „ Z d „ Z d „ Z d „ Z d „ Z RS( c C s˜ d } t d d | ƒ} t ƒ } | j | j | ƒ t d d d d ƒ t d d d d ƒ t d d
d d ƒ t d d d d
ƒ t d d d d ƒ g ƒ d S( Nsh Page title<title>
<body><p><a href="item/12.html">Item 12</a></p>
<p><a href="/about.html">About us</a></p>
<img src="/logo.png" alt="Company logo (not a link)" />
<p><a href="../othercat.html">Other category</a></p>
<p><a href="/">>></a></p>
<p><a href="/" /></p>
</body></html>s& http://example.org/somepage/index.htmlt bodyt urls( http://example.org/somepage/item/12.htmlt texts Item 12s http://example.org/about.htmls About uss http://example.org/othercat.htmls Other categorys http://example.org/s >>t ( R R t assertEqualt
extract_linksR ( t selft htmlt responset lx( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt
test_basic
s c C sÖ d } t d d | ƒ} t ƒ } | j | j | ƒ t d d d d ƒ g ƒ d } t d d | ƒ} | j | j | ƒ t d d
d d ƒ g ƒ d } t d d | ƒ} | j | j | ƒ t d d d d ƒ g ƒ d S(
NsŸ <html><head><title>Page title<title><base href="http://otherdomain.com/base/" />
<body><p><a href="item/12.html">Item 12</a></p>
</body></html>s& http://example.org/somepage/index.htmlR
R s( http://otherdomain.com/base/item/12.htmlR s Item 12s{ <html><head><title>Page title<title><base href="/" />
<body><p><a href="item/12.html">Item 12</a></p></body></html>s' https://example.org/somepage/index.htmls https://example.org/item/12.htmls— <html><head><title>Page title<title><base href="//noschemedomain.com/path/to/" />
<body><p><a href="item/12.html">Item 12</a></p></body></html>s/ https://noschemedomain.com/path/to/item/12.html( R R R R R ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt
test_base_url s c C sV d } t d d | d d ƒ} t ƒ } | j | j | ƒ t d d d d ƒ g ƒ d S(
Ns> <body><p><a href="item/12.html">Wrong: í</a></p></body></html>s http://www.example.comR
t encodings utf-8R s# http://www.example.com/item/12.htmlR u
Wrong: �( R R R R R ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_link_text_wrong_encoding8 s
c C sL t d d ƒ } t d d d | d i d g d 6ƒ } t d d d | ƒ } t d d
ƒ } t d d d | ƒ } t ƒ } | j | j | ƒ t d d d
d ƒ t d d d
d j d ƒ ƒ g ƒ | j | j | ƒ t d d d
d ƒ t d d d
d j d ƒ ƒ g ƒ | j | j | ƒ t d d d
d ƒ t d d d
d j d ƒ ƒ g ƒ d S( Nt link_extractors linkextractor_noenc.htmlR s http://example.com/utf8R
t headerss text/html; charset=utf-8s Content-Types http://example.com/noencs linkextractor_latin1.htmls http://example.com/latin1s% http://example.com/sample_%C3%B1.htmlR R
s( http://example.com/sample_%E2%82%AC.htmls sample € texts utf-8s" http://example.com/sample_%F1.htmls" http://example.com/sample_%E1.htmls
sample á textt latin1( R R R R R R t decode( R R
t
response_utf8t response_noenct response_latin1R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_extraction_encoding@ s % ""c C sK d } d } t ƒ } | j | j | ƒ t ƒ | j | j | ƒ t ƒ d S( Ns# http://lotsofstuff.com/stuff1/indexs( http://evenmorestuff.com/uglystuff/index( R R t matchest True( R t url1t url2R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_matchesW s
c
C s d } t d d | ƒ} t ƒ } | j g | j | ƒ D] } | ^ q7 t d d d d d t ƒ t d d d d
d t ƒ g ƒ d S( Ns…
<a href="page.html?action=print" rel="nofollow">Printer-friendly page</a>
<a href="about.html">About us</a>
s http://example.org/page.htmlR
R s) http://example.org/page.html?action=printR u Printer-friendly paget nofollows http://example.org/about.htmlu About us( R R R R R R! t False( R R R R t link( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_link_nofollow_ s %( t __name__t
__module__R R R R R$ R( ( ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyR s t SgmlLinkExtractorTestCasec B sÔ e Z e Z d „ Z d „ Z d „ Z d „ Z d „ Z d „ Z d „ Z
d „ Z d „ Z d „ Z
d
„ Z d „ Z d „ Z d
„ Z d „ Z d „ Z d „ Z d „ Z d „ Z d „ Z d „ Z d „ Z RS( c C s+ t d d ƒ } t d d d | ƒ | _ d S( NR s sgml_linkextractor.htmlR s http://example.com/indexR
( R R R ( R R
( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt setUpo s c C s9 | j ƒ } | j t d „ | j | j ƒ Dƒ ƒ ƒ d S( sJ Test that the resulting urls are regular strings and not a unicode objectsc s s! | ] } t | j t ƒ Vq d S( N( t
isinstanceR t str( t .0R' ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pys <genexpr>v s N( t
extractor_clst
assertTruet allR R ( R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_urls_types s c C sÔ | j ƒ } | j g | j | j ƒ D] } | ^ q% t d d d d ƒ t d d d d ƒ t d d d d ƒ t d d d d ƒ t d d
d d ƒ g ƒ | j d d ƒ } | j g | j | j ƒ D] } | ^ qÀ t d d d d ƒ t d d d d ƒ t d d d d ƒ g ƒ | j d d d t ƒ } | j g | j | j ƒ D] } | ^ q=t d d d d ƒ t d d d d ƒ t d d d d ƒ t d d d d ƒ g ƒ | j d d ƒ } | j g | j | j ƒ D] } | ^ qÆt d d d d ƒ t d d d d ƒ t d d d d ƒ g ƒ | j d d d d ƒ } | j g | j | j ƒ D] } | ^ qCt d d d d ƒ t d d d d ƒ g ƒ | j d d ƒ } | j g | j | j ƒ D] } | ^ q¨t d d d d ƒ g ƒ d S( s9 Test the extractor's behaviour among different situationsR s http://example.com/sample1.htmlR u s http://example.com/sample2.htmlu sample 2s http://example.com/sample3.htmlu
sample 3 texts http://www.google.com/somethings http://example.com/innertag.htmlu inner tagt allowt samplet uniqueu sample 3 repetitiont denyt 3t
allow_domainss
google.comN( s sample( s sample( s sample( s sample( R8 ( s
google.com( R0 R R R R R& ( R R R' ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_extractionx s< ((((((c C sŒ | j d d ƒ } | j g | j | j ƒ D] } | ^ q+ t d d d d ƒ t d d d d ƒ t d d d d
ƒ g ƒ | j d d d d ƒ } | j g | j | j ƒ D] } | ^ q¨ t d d d d ƒ t d d d d ƒ g ƒ | j d
d ƒ } | j g | j | j ƒ D] } | ^ q
t d d d d ƒ g ƒ | j d d ƒ } | j g | j | j ƒ D] } | ^ q`t d d d d ƒ g ƒ d S( s9 Test the extractor's behaviour among different situationsR4 R5 R s http://example.com/sample1.htmlR u s http://example.com/sample2.htmlu sample 2s http://example.com/sample3.htmlu
sample 3 textR7 R8 R9 s
google.coms http://www.google.com/somethingt deny_domainss example.comN( R0 R R R R ( R R R' ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt# test_extraction_using_single_values¥ s ((((c C s d } t d d | ƒ} | j ƒ } | j | j | ƒ t d d d d ƒ t d d d d ƒ t d d
d d d t ƒ t d d
d d ƒ g ƒ d S( s< Test the extractor's behaviour for links with rel="nofollow"sÙ <html><head><title>Page title<title>
<body>
<div class='links'>
<p><a href="/about.html">About us</a></p>
</div>
<div>
<p><a href="/follow.html">Follow this link</a></p>
</div>
<div>
<p><a href="/nofollow.html" rel="nofollow">Dont follow this one</a></p>
</div>
<div>
<p><a href="/nofollow2.html" rel="blah">Choose to follow or not</a></p>
</div>
</body></html>s& http://example.org/somepage/index.htmlR
R s http://example.org/about.htmlR u About uss http://example.org/follow.htmlu Follow this links http://example.org/nofollow.htmlu Dont follow this oneR% s! http://example.org/nofollow2.htmlu Choose to follow or notN( R R0 R R R R! ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt
test_nofollow¿ s c C s¨ d } d } | j d d ƒ } | j | j | ƒ t ƒ | j | j | ƒ t ƒ | j d d ƒ } | j | j | ƒ t ƒ | j | j | ƒ t ƒ | j d d ƒ } | j | j | ƒ t ƒ | j | j | ƒ t ƒ | j d d ƒ } | j | j | ƒ t ƒ | j | j | ƒ t ƒ | j d d d d d d d d ƒ } | j | j d ƒ t ƒ | j | j d ƒ t ƒ | j | j d ƒ t ƒ | j | j d ƒ t ƒ d S( Ns# http://lotsofstuff.com/stuff1/indexs( http://evenmorestuff.com/uglystuff/indexR4 t stuff1R7 t uglystuffR9 s evenmorestuff.comR; s lotsofstuff.comt blah1t blah2s blah1.coms blah2.coms http://blah1.com/blah1s http://blah1.com/blah2s http://blah2.com/blah1s http://blah2.com/blah2( R> ( R? ( s evenmorestuff.com( s lotsofstuff.com( R@ ( RA ( s blah1.com( s blah2.com( R0 R R R! R& ( R R" R# R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyR$ Û s* c C si | j d d ƒ } | j g | j | j ƒ D] } | ^ q+ t d d d d ƒ t d d d d ƒ g ƒ d S(
Nt restrict_xpathss //div[@id="subwrapper"]R s http://example.com/sample1.htmlR u s http://example.com/sample2.htmlu sample 2( s //div[@id="subwrapper"]( R0 R R R R ( R R R' ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_restrict_xpaths÷ s (c C s_ d } t d d | d d ƒ} | j d d ƒ } | j | j | ƒ t d d d
d ƒ g ƒ d S(
s# Test restrict_xpaths with encodingss5 <html><head><title>Page title<title>
<body><p><a href="item/12.html">Item 12</a></p>
<div class='links'>
<p><a href="/about.html">About us£</a></p>
</div>
<div>
<p><a href="/nofollow.html">This shouldn't be followed</a></p>
</div>
</body></html>s& http://example.org/somepage/index.htmlR
R s windows-1252RB s //div[@class='links']R s http://example.org/about.htmlR u
About us£N( R R0 R R R ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_restrict_xpaths_encodingþ s
c C s\ d } t d d | d d ƒ} t d d ƒ j | ƒ } | j | t d d d
d ƒ g ƒ d S( NsJ <html><body><p><a href="/♥/you?c=€">text</a></p></body></html>s& http://example.org/somepage/index.htmlR
R s
iso8859-15RB s //pR s, http://example.org/%E2%99%A5/you?c=%E2%82%ACR u text( R R R R R ( R R R t links( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt' test_restrict_xpaths_with_html_entities s
c C sk d } t d d | d d ƒ} | j d d ƒ } | j | j | ƒ t d d d
d d d
d t ƒ g ƒ d S( s= html entities cause SGMLParser to call handle_data hook twices> <html><body><div><a href="/foo">>¾©<¶«</a></body></html>s http://example.orgR
R t gb18030RB s //divR s http://example.org/fooR u >京<东t fragmentR
R% N( R R0 R R R R& ( R R
R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt* test_restrict_xpaths_concat_in_handle_data s c C sD | j d d ƒ } | j | j | j ƒ t d d d d ƒ g ƒ d S( Nt restrict_csss
#subwrapper aR s http://example.com/sample2.htmlR u sample 2( s
#subwrapper a( R0 R R R R ( R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_restrict_css s c C s | j d d
d d ƒ } | j g | j | j ƒ D] } | ^ q1 t d d d d ƒ t d d d d
ƒ t d d d d ƒ g ƒ d S( NRB s //div[@id="subwrapper"]RJ s #subwrapper + aR s http://example.com/sample1.htmlR u s http://example.com/sample2.htmlu sample 2s http://example.com/sample3.htmlu
sample 3 text( s //div[@id="subwrapper"]( s #subwrapper + a( R0 R R R R ( R R R' ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt. test_restrict_css_and_restrict_xpaths_together% s (c C sŒ d } t d d | d d ƒ} | j ƒ } | j | ƒ | j | ƒ | j | ƒ | j | j | ƒ t d d d d d
d d t ƒ g ƒ d S(
NsM <html><body>¾©<map><area href="http://example.org/foo" /></map></body></html>s http://example.orgR
R s utf-8R s http://example.org/fooR u RH R
R% ( R R0 R R R R& ( R R
R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt" test_area_tag_with_unicode_present. s
c C se d } t d d | d d ƒ} | j ƒ } | j | j | ƒ t d d d d d
d d t ƒ g ƒ d S(
Ns9 <html><body><div><a href="?page=2">BinB</a></body></html>s http://known.fm/AC%2FDC/R
R t utf8R s http://known.fm/AC%2FDC/?page=2R u BinBRH R
R% ( R R0 R R R R& ( R R
R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_encoded_url9 s
c C sk d } t d d | d d ƒ} | j d d ƒ } | j | j | ƒ t d d d
d d d
d t ƒ g ƒ d S( Ns9 <html><body><div><a href="?page=2">BinB</a></body></html>s http://known.fm/AC%2FDC/R
R RN RB s //divR s http://known.fm/AC%2FDC/?page=2R u BinBRH R
R% ( R R0 R R R R& ( R R
R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt$ test_encoded_url_in_restricted_xpathA s
c C s d } t d d | ƒ} | j ƒ } | j | j | ƒ t d d d d ƒ g ƒ t d d ƒ } | j | j | ƒ t d d d d ƒ g ƒ d S(
Ns4 <a href="page.html">asd</a> and <a href="photo.jpg">s http://example.org/R
R s http://example.org/page.htmlR u asdt deny_extensionst jpg( R R0 R R R R ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_deny_extensionsI s c C sh d } t d d | d d ƒ} d „ } | j d | ƒ } | j | j | ƒ t d d d
d ƒ g ƒ d S(
s# Test restrict_xpaths with encodingss¶
<a href="javascript:goToPage('../other/page.html','photo','width=600,height=540,scrollbars'); return false">Link text</a>
<a href="/about.html">About us</a>
s& http://example.org/somepage/index.htmlR
R s windows-1252c S s) t j d | ƒ } | r% | j d ƒ Sd S( Ns javascript:goToPage\('(.*?)'i ( t ret searcht group( t valuet m( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt
process_value^ s RY R s" http://example.org/other/page.htmlR s Link textN( R R0 R R R ( R R R RY R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_process_valueV s c C sY d } t d d | ƒ} | j d d ƒ } | j | j | ƒ t d d d d ƒ g ƒ d S(
NsŸ <html><head><title>Page title<title><base href="http://otherdomain.com/base/" />
<body><p><a href="item/12.html">Item 12</a></p>
</body></html>s& http://example.org/somepage/index.htmlR
RB s //pR s( http://otherdomain.com/base/item/12.htmlR s Item 12( R R0 R R R ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt" test_base_url_with_restrict_xpathsg s
c C s² | j d d ƒ } | j | j | j ƒ t d d d d ƒ t d d d d ƒ t d d d d
ƒ t d d d d ƒ t d d d d
ƒ g ƒ | j d d d d d d ƒ } | j | j | j ƒ t d d d d ƒ t d d d d ƒ t d d d d ƒ t d d d d
ƒ t d d d d ƒ t d d d d
ƒ g ƒ | j d d ƒ } | j | j | j ƒ g ƒ d } t d d | ƒ} t d d ƒ } | j | j | ƒ t d d d d ƒ g ƒ d S( Nt attrst hrefR s http://example.com/sample1.htmlR u s http://example.com/sample2.htmlu sample 2s http://example.com/sample3.htmlu
sample 3 texts http://www.google.com/somethings http://example.com/innertag.htmlu inner tagt srct tagst at areat imgRQ s http://example.com/sample2.jpgsU <html><area href="sample1.html"></area><a ref="sample2.html">sample text 2</a></html>s http://example.com/index.htmlR
( s hrefs src( R` s areas img( ( R0 R R R R t NoneR R ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt
test_attrsp s, c C se d } t d d | ƒ} | j d d ƒ } | j | j | ƒ g ƒ | j ƒ } | j | j | ƒ t d d d d ƒ t d d d d
ƒ g ƒ | j d d ƒ } | j | j | ƒ t d d d d ƒ g ƒ | j d d ƒ } | j | j | ƒ t d d d d
ƒ g ƒ | j d d d d d d ƒ } | j | j | ƒ t d d d d
ƒ t d d d d ƒ g ƒ d S( Nsi <html><area href="sample1.html"></area><a href="sample2.html">sample 2</a><img src="sample2.jpg"/></html>s http://example.com/index.htmlR
R_ R s http://example.com/sample1.htmlR u s http://example.com/sample2.htmlu sample 2Ra R` Rb R\ R] R^ RQ s http://example.com/sample2.jpg( R` s img( s hrefs src( ( R R0 Rc R R R ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_tagsŽ s$ c C sö d } t d d | ƒ} | j d d d d ƒ } | j | j | ƒ t d d d
d d d
d t ƒ t d d d
d d d
d t ƒ g ƒ | j d d d d ƒ } | j | j | ƒ t d d d
d d d
d t ƒ t d d d
d d d
d t ƒ g ƒ d S( NsÇ
<html><body>
<div id="item1" data-url="get?id=1"><a href="#">Item 1</a></div>
<div id="item2" data-url="get?id=2"><a href="#">Item 2</a></div>
</body></html>
s http://example.com/index.htmlR
R_ t divR\ s data-urlR s http://example.com/get?id=1R u Item 1RH R
R% s http://example.com/get?id=2u Item 2( s div( s data-url( R R0 R R R R& ( R R R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt test_tags_attrs« s % c C sh d } t d d | ƒ} | j ƒ } | j | j | ƒ t d d d d d d d
t ƒ t d d d d d d d
t ƒ t d d
d d d d d
t ƒ t d d d d d d d
t ƒ g ƒ t d d | ƒ} | j ƒ } | j | j | ƒ t d d d d d d d
t ƒ t d d d d d d d
t ƒ t d d
d d d d d
t ƒ t d d d d d d d
t ƒ g ƒ d S( Ns‚
<?xml version="1.0"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title>XHTML document title
s http://example.com/index.xhtmlR
R s http://example.com/about.htmlR u About usRH R
R% s http://example.com/follow.htmlu Follow this links http://example.com/nofollow.htmlu Dont follow this ones! http://example.com/nofollow2.htmlu Choose to follow or not( R R0 R R R R& R! R ( R t xhtmlR R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt
test_xhtmlÀ s % ( R) R* R R0 R, R3 R: R< R= R$ RC RD RF RI RK RL RM RO RP RS RZ R[ Rd Re Rg Ri ( ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyR+ l s. -
t LxmlLinkExtractorTestCasec B s e Z e Z RS( ( R) R* R R0 ( ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyRj ï s t HtmlParserLinkExtractorTestCasec B s e Z d „ Z d „ Z RS( c C s+ t d d ƒ } t d d d | ƒ | _ d S( NR s sgml_linkextractor.htmlR s http://example.com/indexR
( R R R ( R R
( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyR, õ s c C sƒ t ƒ } | j | j | j ƒ t d d d d ƒ t d d d d ƒ t d d d d ƒ t d d d d ƒ t d d
d d ƒ g ƒ d S( NR s http://example.com/sample2.htmlR u sample 2s http://example.com/sample3.htmlu
sample 3 textu sample 3 repetitions http://www.google.com/somethingu s http://example.com/innertag.htmlu inner tag( R R R R R ( R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyR: ù s ( R) R* R, R: ( ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyRk ó s t RegexLinkExtractorTestCasec B s e Z d „ Z d „ Z RS( c C s+ t d d ƒ } t d d d | ƒ | _ d S( NR s sgml_linkextractor.htmlR s http://example.com/indexR
( R R R ( R R
( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyR, s c
C sq t ƒ } | j | j | j ƒ t d d d d ƒ t d d d d ƒ t d d d d ƒ t d d d d
ƒ g ƒ d S( NR s http://example.com/sample2.htmlR u sample 2s http://example.com/sample3.htmlu
sample 3 texts http://www.google.com/somethingu s http://example.com/innertag.htmlu inner tag( R R R R R ( R R ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyR:
s ( R) R* R, R: ( ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyRl s t __main__( RT t unittestt scrapy.linkextractors.regexR t scrapy.httpR R t scrapy.linkR t scrapy.linkextractors.htmlparserR t scrapy.linkextractors.sgmlR R t scrapy.linkextractors.lxmlhtmlR t testsR t TestCaseR R+ Rj Rk Rl R) t main( ( ( s= /home/travis/build/scrapy/scrapy/tests/test_linkextractors.pyt s `ÿ „