Python使用BeautifulSoup包编写爬虫时的一些关键点

November


  2012
  

foundTwoLabel = eachMonthHeader.findAll("label");
print "foundTwoLabel=",foundTwoLabel;
mOnthLabel= foundTwoLabel[0];
yearLabel = foundTwoLabel[1];
 
mOnthStr= monthLabel.string;
yearStr = yearLabel.string;
 
print "mOnthStr=",monthStr; # mOnthStr= November
print "yearStr=",yearStr; # yearStr= 2012

# November
# 
# 
  # 2012
  # 
# 
foundCboMOnth= eachMonthHeader.find("input", {"id":re.compile("cboMonth\d+")});
#print "foundCboMOnth=",foundCboMonth;
tdMOnth= foundCboMonth.parent;
#print "tdMOnth=",tdMonth;
tdMOnthLabel= tdMonth.label;
#print "tdMOnthLabel=",tdMonthLabel;
mOnthStr= tdMonthLabel.string;
print "mOnthStr=",monthStr;
 
foundCboYear = eachMonthHeader.find("input", {"id":re.compile("cboYear\d+")});
#print "foundCboYear=",foundCboYear;
tdYear = foundCboYear.parent;
#print "tdYear=",tdYear;
tdYearLabel = tdYear.label;
#print "tdYearLabel=",tdYearLabel;
yearStr = tdYearLabel.string;
print "yearStr=",yearStr;

from BeautifulSoup import BeautifulSoup 
doc = ['',
    '
This is paragraph one.',
    '
This is paragraph two.',
    '']
soup = BeautifulSoup(''.join(doc))

print soup.prettify()
# 
# 
#  
# 
# 
#  

#  This is paragraph
#  
#   one
#  
#  .
#  
#  

#  This is paragraph
#  
#   two
#  
#  .
#  
# 
# 

soup.head.parent.name
# u'html'
soup.head.parent.parent.__class__.__name__
# 'BeautifulSoup'
soup.parent == None
# True

#这里respHtml是ASCII或UTF-8编码，此时可以不指定编码类型，即可正确解析出对应的soup
soup = BeautifulSoup(respHtml);

#此处respHtml是GB2312编码的，所以要指定该编码类型，BeautifulSoup才能解析出对应的soup
htmlCharset = "GB2312";
soup = BeautifulSoup(respHtml, fromEncoding=htmlCharset);