采集地方报刊电子版本的爬虫

# -*- coding: utf-8 -*- import urllib2 from bs4 import BeautifulSoup import os import re import time import sys ##过滤HTML中的标签 #将HTML中标签等信息去掉 #@param htmlstr HTML字符串. def filter_tags(htmlstr): #先过滤CDATA re_cdata=re.compile('//<!\[CDATA\[[^>]*//\]\]>',re.I) #匹配CDATA re_script=re.compile('<\s*script[^>]*>[^<]*<\s*/\s*script\s*>',re.I)#Script re_style=re.compile('<\s*style[^>]*>[^<]*<\s*/\s*style\s*>',re.I)#style re_br=re.compile('<br\s*?/?>')#处理换行 re_h=re.compile('</?\w+[^>]*>')#HTML标签 re_comment=re.compile('<!--[^>]*-->')#HTML注释 s=re_cdata.sub('',htmlstr)#去掉CDATA s=re_script.sub('',s) #去掉SCRIPT s=re_style.sub('',s)#去掉style s=re_br.sub('\n',s)#将br转换为换行 s=re_h.sub('',s) #去掉HTML 标签 s=re_comment.sub('',s)#去掉HTML注释 #去掉多余的空行 blank_line=re.compile('\n+') s=blank_line.sub('\n',s) s=replaceCharEntity(s)#替换实体 return s ##替换常用HTML字符实体. #使用正常的字符替换HTML中特殊的字符实体. #你可以添加新的实体字符到CHAR_ENTITIES中,处理更多HTML字符实体. #@param htmlstr HTML字符串. def replaceCharEntity(htmlstr): CHAR_ENTITIES={'nbsp':' ','160':' ', 'lt':'<','60':'<', 'gt':'>','62':'>', 'amp':'&','38':'&', 'quot':'"','34':'"',} re_charEntity=re.compile(r'&#?(?P<name>\w+);') sz=re_charEntity.search(htmlstr) while sz: entity=sz.group()#entity全称，如&gt; key=sz.group('name')#去除&;后entity,如&gt;为gt try: htmlstr=re_charEntity.sub(CHAR_ENTITIES[key],htmlstr,1) sz=re_charEntity.search(htmlstr) except KeyError: #以空串代替 htmlstr=re_charEntity.sub('',htmlstr,1) sz=re_charEntity.search(htmlstr) return htmlstr def repalce(s,re_exp,repl_string): return re_exp.sub(repl_string,s) pdf_url="http://wenhui.sumg.com.cn/images/" print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())) source_url = "http://wenhui.sumg.com.cn/html/"+time.strftime("%Y-%m", time.localtime())+"/"+time.strftime("%d", time.localtime())+"/"+sys.argv[1] print source_url home_path = "/usr/crawler/wenhui/" disk0 = "/usr/crawler/program/" # 获取某个版面 date_dir=home_path+time.strftime("%Y%m%d", time.localtime())+"/"+sys.argv[2] home_out = open(date_dir + "/"+sys.argv[1]+".txt", 'w') print "-----------------------------------------------" news_web_response = urllib2.urlopen(source_url) news_readable_page = news_web_response.read() news_soup = BeautifulSoup(news_readable_page, "lxml") home_out.write(u"标题\n".encode('utf-8')) title_soup0 = news_soup.find(name="h1", attrs={"class": "title1"}) home_out.write(filter_tags(title_soup0.prettify().encode('utf-8'))) title_soup = news_soup.find(name="h1", attrs={"class": "title"}) home_out.write(filter_tags(title_soup.prettify().encode('utf-8'))) title_soup2 = news_soup.find(name="h2", attrs={"class": "title2"}) home_out.write(filter_tags(title_soup2.prettify().encode('utf-8'))) home_out.write(u"正文\n".encode('utf-8')) content_soup = news_soup.find(name="div", attrs={"class": "articleText textLR"}) home_out.write(filter_tags(content_soup.prettify().encode('utf-8'))) img_soup2 = news_soup.find(name="table", attrs={"id": "tableInfo"}) if img_soup2 is not None: #home_out.write(img_soup2.prettify().encode('utf-8')) image_soup=img_soup2.find_all(name="img") if image_soup is not None: home_out.write(u"\n\n插图URL\n".encode('utf-8')) #home_out.write(image_soup.prettify().encode('utf-8')) for image_line in image_soup: image_link = image_line.get('src') print image_link image_name = image_link[image_link.rfind('/')+1:] image_link=image_link.replace("../../../images/"+time.strftime("%Y-%m", time.localtime())+"/"+time.strftime("%d", time.localtime())+"/","") home_out.write("\n"+image_link+"\n") image_name = image_link[image_link.rfind('/')+1:] image_dir=date_dir +"/"+sys.argv[1] if not os.path.exists(image_dir): os.makedirs(image_dir) image = urllib2.urlopen(pdf_url+time.strftime("%Y-%m", time.localtime())+"/"+time.strftime("%d", time.localtime())+"/"+image_link).read() with open(image_dir +"/"+ image_name, 'wb') as code: code.write(image) code.close() home_out.close()