Regex AttributeError:基于重新编译模式
我是Python的新手,我很确定这仅仅是一个金发女郎的时刻,但这几天我一直被它逼疯了 我一直在第106行看到“elif conName.search(line):AttributeError:'list'对象没有属性'search'” 如果我将第54行中的模式替换为第50行中的模式,那么第106-113行运行良好,但在第114行得到相同的错误Regex AttributeError:基于重新编译模式,regex,python-3.x,Regex,Python 3.x,我是Python的新手,我很确定这仅仅是一个金发女郎的时刻,但这几天我一直被它逼疯了 我一直在第106行看到“elif conName.search(line):AttributeError:'list'对象没有属性'search'” 如果我将第54行中的模式替换为第50行中的模式,那么第106-113行运行良好,但在第114行得到相同的错误 ## This should be line 19 html_doc = """ <title>Flickr: userna
## This should be line 19
html_doc = """
<title>Flickr: username</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<meta property="og:title" content="username" />
<meta property="og:type" content="flickr_photos:profile" />
<meta property="og:url" content="http://www.flickr.com/people/Something/" />
<meta property="og:site_name" content="Flickr" />
<meta property="og:image" content="http://farm79.staticflickr.com/1111/buddyicons/99999999@N99.jpg?1234567890#99999999@N99" />
<li>
<a href="/groups/theportraitgroup/">The Portrait Group</a>
<span class="text-list-item">
1,939,830 photos, 125,874 members
</span>
</li>
<li>
<a href="/groups/412762@N20/">Seagulls Gone Wild</a>
<span class="text-list-item">
2,266 photos, 464 members
</span>
</li> """
from urllib.request import urlopen
from bs4 import BeautifulSoup
import fileinput
import re
## This should be line 46
## Strips for basic group data
Tab = re.compile("(\t){1,}") # strip tabs
ID = re.compile("^.*/\">") # Group ID, could be ID or Href
Href = re.compile("(\s)*<a href=\"/groups/") # Strips to beginning of ID
GName = re.compile("/\">(<b>)*") # Strips from end of Href to GName
## Persons contact info
conName = re.compile("(\s)*<meta property=\"og\:title\" content=\"") # Contact Name
##conName = re.compile("(\s)*<a href=\"/groups/")
conID = re.compile("(\s)*<meta property=\"og\:image.*\#") # Gets conName's @N ID
conRef = re.compile("(\s)*<meta property=\"og\:url.*com/people/")
Amp = re.compile("&")
Qt = re.compile(""")
Gt = re.compile(">")
Lt = re.compile("<")
exfile = 1 ## 0 = use internal data, 1 = use external file
InFile = html_doc
if exfile:
InFile = open('\Python\test\Group\group 50 min.ttxt', 'r', encoding = "utf-8", errors = "backslashreplace")
closein = 1 ## Only close input file if it was opened
else:
closein = 0
OutFile = open('C:\Python\test\Group\Output.ttxt', 'w', encoding = "utf-8", errors = "backslashreplace")
cOutFile = open('C:\Python\test\Group\ContactOutput.ttxt', 'w', encoding = "utf-8", errors = "backslashreplace")
i = 1 ## counter for debugging
## This should be line 80
for line in InFile:
## print('{}'.format(i), end = ', ') ## this is just a debugging line, to see where the program errors out
## i += 1
if Href.search(line):
ln = line
ln = re.sub(Href, "", ln)
gID, Name = ln.split("/\">")
Name = Name[:-5] ## this removes the "\n" at EOL as well
if "@N" in gID:
rH = ""
else:
rH = gID
gID = ""
## sLn = '{3}\t{0}\t{1}\t{2}\n'.format(Name, gID, rH, conName)
sLn = '{0}\t{1}\t{2}\n'.format(Name, gID, rH, conName)
## Replace HTML codes
sLn = re.sub(Gt, ">", sLn)
sLn = re.sub(Lt, "<", sLn)
sLn = re.sub(Qt, "\"", sLn)
sLn = re.sub(Amp, "&", sLn)
OutFile.write(sLn)
## This should be line 104
#################################################
elif conName.search(line):
ln = line
ln = re.sub(conName, "", ln)
conName = ln.split("\" />")
elif conID.search(line) is not None:
ln = line
ln = re.sub(conID, "", ln)
conID = ln.split("\" />")
elif conRef.search(line) is not None:
ln = line
ln = re.sub(conRef, "", ln)
conRef = ln.split("\" />")
else:
pass
sLn = '{0}\t{1}\t{2}\n'.format(conID, conRef, conName)
cOutFile.write(sLn) ## I know, this will make a massive file with duplicated data, but deal w/ it later
#################################################
if closein:
InFile.close()
OutFile.close()
cOutFile.close()
当我注释掉第105-123行时,代码的其余部分工作得最好
当我注释掉第106-109行时,第110-113行运行良好,但在第114行得到相同的错误
## This should be line 19
html_doc = """
<title>Flickr: username</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<meta property="og:title" content="username" />
<meta property="og:type" content="flickr_photos:profile" />
<meta property="og:url" content="http://www.flickr.com/people/Something/" />
<meta property="og:site_name" content="Flickr" />
<meta property="og:image" content="http://farm79.staticflickr.com/1111/buddyicons/99999999@N99.jpg?1234567890#99999999@N99" />
<li>
<a href="/groups/theportraitgroup/">The Portrait Group</a>
<span class="text-list-item">
1,939,830 photos, 125,874 members
</span>
</li>
<li>
<a href="/groups/412762@N20/">Seagulls Gone Wild</a>
<span class="text-list-item">
2,266 photos, 464 members
</span>
</li> """
from urllib.request import urlopen
from bs4 import BeautifulSoup
import fileinput
import re
## This should be line 46
## Strips for basic group data
Tab = re.compile("(\t){1,}") # strip tabs
ID = re.compile("^.*/\">") # Group ID, could be ID or Href
Href = re.compile("(\s)*<a href=\"/groups/") # Strips to beginning of ID
GName = re.compile("/\">(<b>)*") # Strips from end of Href to GName
## Persons contact info
conName = re.compile("(\s)*<meta property=\"og\:title\" content=\"") # Contact Name
##conName = re.compile("(\s)*<a href=\"/groups/")
conID = re.compile("(\s)*<meta property=\"og\:image.*\#") # Gets conName's @N ID
conRef = re.compile("(\s)*<meta property=\"og\:url.*com/people/")
Amp = re.compile("&")
Qt = re.compile(""")
Gt = re.compile(">")
Lt = re.compile("<")
exfile = 1 ## 0 = use internal data, 1 = use external file
InFile = html_doc
if exfile:
InFile = open('\Python\test\Group\group 50 min.ttxt', 'r', encoding = "utf-8", errors = "backslashreplace")
closein = 1 ## Only close input file if it was opened
else:
closein = 0
OutFile = open('C:\Python\test\Group\Output.ttxt', 'w', encoding = "utf-8", errors = "backslashreplace")
cOutFile = open('C:\Python\test\Group\ContactOutput.ttxt', 'w', encoding = "utf-8", errors = "backslashreplace")
i = 1 ## counter for debugging
## This should be line 80
for line in InFile:
## print('{}'.format(i), end = ', ') ## this is just a debugging line, to see where the program errors out
## i += 1
if Href.search(line):
ln = line
ln = re.sub(Href, "", ln)
gID, Name = ln.split("/\">")
Name = Name[:-5] ## this removes the "\n" at EOL as well
if "@N" in gID:
rH = ""
else:
rH = gID
gID = ""
## sLn = '{3}\t{0}\t{1}\t{2}\n'.format(Name, gID, rH, conName)
sLn = '{0}\t{1}\t{2}\n'.format(Name, gID, rH, conName)
## Replace HTML codes
sLn = re.sub(Gt, ">", sLn)
sLn = re.sub(Lt, "<", sLn)
sLn = re.sub(Qt, "\"", sLn)
sLn = re.sub(Amp, "&", sLn)
OutFile.write(sLn)
## This should be line 104
#################################################
elif conName.search(line):
ln = line
ln = re.sub(conName, "", ln)
conName = ln.split("\" />")
elif conID.search(line) is not None:
ln = line
ln = re.sub(conID, "", ln)
conID = ln.split("\" />")
elif conRef.search(line) is not None:
ln = line
ln = re.sub(conRef, "", ln)
conRef = ln.split("\" />")
else:
pass
sLn = '{0}\t{1}\t{2}\n'.format(conID, conRef, conName)
cOutFile.write(sLn) ## I know, this will make a massive file with duplicated data, but deal w/ it later
#################################################
if closein:
InFile.close()
OutFile.close()
cOutFile.close()
##这应该是第19行
html_doc=“”
Flickr:用户名
1939830张照片,125874名成员
2266张照片,464名成员
“”“
从urllib.request导入urlopen
从bs4导入BeautifulSoup
导入文件输入
进口稀土
##这应该是第46行
##用于基本组数据的条带
Tab=re.compile(“(\t){1,}”)#条带制表符
ID=re.compile(“^.*/\”>”)组ID,可以是ID或Href
Href=re.compile(“(\s)*()*”)#从Href末尾到GName的条带
##个人联系信息
conName=re.compile(“(\s)*
我一直在第106行看到“elif conName.search(line):AttributeError:'list'对象没有属性'search'”
这意味着此时conName
是一个列表。实际上,下面两行将conName
分配给列表:
conName = ln.split("\" />")
在第一次conName.search()
返回一个成功匹配后,您将其更改为一个列表,因此对于文件中的以下行(下一次循环迭代)conName.search
会产生错误
我一直在第106行看到“elif conName.search(line):AttributeError:'list'对象没有属性'search'”
这意味着此时conName
是一个列表。实际上,下面两行将conName
分配给列表:
conName = ln.split("\" />")
在第一次conName.search()
返回一个成功匹配后,您将其更改为一个列表,以便用于文件中的以下行(下一次循环迭代)conName.search
产生错误。我看到您有来自bs4的导入BeautifulSoup
为什么不使用它来解析html片段而不是正则表达式?我看到您有来自bs4导入BeautifulSoup的为什么不使用它来解析html片段而不是正则表达式?谢谢!这非常有效,并且我玩过一点BS,但我既不懂Python也不懂BS,我觉得最好一次只玩一个!;)谢谢!这非常有效,并且节省了大量的头发拉扯!我玩过一点BS,但我既不懂Python也不懂BS,我认为最好一次只玩一个