def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://www.81.cn/rd/node_92585%s.htm"
for i in range(1, 6):
ss = ''
if (i == 1):
ss = ''
else:
ss = '_%d' % i
url = start_url % (ss)
#print(url)
list_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(list_html)
colum = [('a', '//div[@class="content"]//ul//li//a//@href', 'sab',
'http://www.81.cn/rd/')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=url)
#print(list)
for a in list[0][1]:
read_detial(a, i)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://junshi.xilu.com/dfjs/index_1372_%d.html"
for i in range(1, 101):
url = start_url % (i)
#print(url)
list_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(list_html)
colum = [(
'a',
'//div[@class="newslist_box"]//ul//li//div[@class="newslist_tit"]//a//@href',
'l')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=url)
#print(list)
for a in list[0][1]:
read_detial(a, i)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://mil.huanqiu.com/world/%s.html"
for i in range(1, 101):
s = 'index'
if (i == 1):
s = 'index'
else:
s = i
url = start_url % (s)
#print(url)
list_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(list_html)
colum = [('a', '//div[@class="fallsFlow"]//ul//li//a//@href', 'l')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=url)
#print(list)
for a in list[0][1]:
read_detial(a, i)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://www.cankaoxiaoxi.com/mil/gjjq/%d.shtml"
for i in range(1, 101):
url = start_url % (i)
#print(url)
list_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(list_html)
colum = [(
'a',
'//div[@class="inner"]//ul[@class="txt-list-a fz-14"]//li//a//@href',
'sab', '')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=url)
#print(list)
for a in list[0][1]:
read_detial(a, i)
def read_detial(url, i):
detial_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(detial_html)
# 写html
files = File_file()
names = url.split('/')
file_name = names[len(names) - 1]
files.save_source(path=path,
file=file_name,
all_the_text=detial_html,
encoding_='utf-8')
colum = [
('title', '//h1[@class="articleHead"]//text()', 'l'),
('pushDate',
'//div[@class="info"]//span[@class="infoA"][@id="pubtime_baidu"]//text()',
'l'), ('content', '//div[@class="articleText"]//text()', 'sarra', ',')
]
result = rule.html_content_analysis_detial(html_text=detial_html,
column=colum,
url=url)
print(result)
#sql="insert into cancer value('%s','%s','%s','%s','%s')"%(result[0][1][0],str(result[1][1][0]).replace('患者,图片因隐私问题无法显示','').replace("患者,","患者:").replace("医生,","医生:").replace('\'','"'),type,'春雨医生',url)
#print(sql)
# 写文件
# web_name（网站名）、web_url（网址）、titile（标题）、text（新闻内容）、publish_date（发布时间）
csv = Csv_base()
csv.write_csv_file_line(file_path=path + "/data.csv",
str=[
'参考消息', url, result[0][1], result[1][1],
result[2][1], i,
time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
])
def runDict(self, url, conf):
rule = Rule()
result = rule.crawler_list(url, conf)
# 数据入库 TODO
dic_list = []
for row in conf['columns']:
dic_list.append(row['名称'])
# 文件写入文件
csv = Csv_base()
csv.write_csv_file_dictLines(file_path='../data/xuexi111.csv',
strs=result,
fieldnames=dic_list)
def runDetail(self, file_path, confs, listconfs):
csv = Csv_base()
# 数据读取
for listconf in listconfs:
dic_list = []
for row in listconf['columns']:
dic_list.append(row['名称'])
listList = csv.read_csv_file_dict(file_path=file_path,
fieldnames=dic_list)
for row in listList:
self.crawlerDetail(confs, url=row[confs['urlname']])
def runList(self, file_path, confs, dictconf):
csv = Csv_base()
# 数据读取
dic_list = []
for row in dictconf['columns']:
dic_list.append(row['名称'])
dictList = csv.read_csv_file_dict(file_path=file_path,
fieldnames=dic_list)
# 数据写入
for dict in dictList:
for conf in confs:
self.crawlerNext(conf, url=dict[conf['urlname']])
def crawlerNext(self, conf, url=''):
rule = Rule()
csv = Csv_base()
list_list = []
for row in conf['columns']:
list_list.append(row['名称'])
result, next_page = rule.crawler_list(url, conf)
print(result)
if (len(result) > 0):
csv.write_csv_file_dictLines(file_path='../data/xuexi111List.csv',
strs=result,
fieldnames=list_list)
if (next_page):
self.crawlerNext(conf, url=next_page)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://qc.wa.news.cn/nodeart/list?nid=11139636&pgnum=%d&cnt=1000&tp=1&orderby=1"
for i in range(1, 6):
url = start_url % (i)
read_detial(url, i)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(file_path=path+"/data.csv",mode='w+',str=['网站名','网址','标题','新闻内容','发布时间','页码','采集时间'])
# 爬虫
start_url = "https://www.thepaper.cn/load_index.jsp?nodeids=25430&topCids=&pageidx=%d&isList=true&lastTime=1550211962471"
for i in range(1,26):
url = start_url%(i)
#print(url)
list_html = htmlSource.get_html(url_p=url,type_p='rg')
#print(list_html)
colum=[('a','//div[@class="news_li"]//h2//a//@href','sab','https://www.thepaper.cn/')]
list = rule.html_content_analysis_detial(html_text=list_html,column=colum,url=url)
#print(list)
for a in list[0][1]:
read_detial(a,i)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '采集时间'])
# 爬虫
start_url = "https://military.china.com/news/"
#print(url)
list_html = htmlSource.get_html(url_p=start_url, type_p='rg')
#print(list_html)
colum = [('a', '//div[@class="column-list"]//h3[@class="tit"]//a//@href',
'l')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=start_url)
#print(list)
for a in list[0][1]:
read_detial(a)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://mil.news.sina.com.cn/roll/index.d.html?cid=57919&page=%d"
for i in range(1, 26):
url = start_url % (i)
#print(url)
list_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(list_html)
colum = [('a', '//div[@class="fixList"]//ul//li//a//@href', 'l')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=url)
#print(list)
for a in list[0][1]:
if (a[len(a) - 6:] == '.shtml'):
read_detial(a, i)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://military.people.com.cn/GB/1077/index%d.html"
for i in range(1, 8):
url = start_url % (i)
#print(url)
list_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(list_html)
colum = [('a', '//div[@class="ej_list_box clear"]//ul//li//a//@href',
'sab', 'http://military.people.com.cn')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=url)
#print(list)
for a in list[0][1]:
read_detial(a, i)
def main():
floder = File_floder()
floder.add(path_p=path)
csv = Csv_base()
csv.write_csv_file_line(
file_path=path + "/data.csv",
mode='w+',
str=['网站名', '网址', '标题', '新闻内容', '发布时间', '页码', '采集时间'])
# 爬虫
start_url = "http://www.dsti.net/Information/HyeList/arms/%d"
for i in range(1, 815):
url = start_url % (i)
#print(url)
list_html = htmlSource.get_html(url_p=url, type_p='rg')
#print(list_html)
colum = [('a', '//div[@class="listMidContent"]//ul//li//a//@href',
'sab', 'http://www.dsti.net')]
list = rule.html_content_analysis_detial(html_text=list_html,
column=colum,
url=url)
#print(list)
for a in list[0][1]:
read_detial(a, i)
#!/usr/bin/env python
# coding=utf-8
from common.inc_csv import Csv_base
from lxml import html
import re
def readFile(filePath=''):
pass
if __name__ == '__main__':
filepath = '../data/问答语料_1.0.txt'
file = Csv_base()
list = file.read_csv_file(filepath)
for i in range(len(list)):
if (i > 3):
row = list[i]
rows = str(row[0]).split("\t")
html_text = rows[1].replace("[", '').replace("]", "")
# 正则匹配 re.match从字符串起始处匹配。
html_text = re.sub(re.compile(r"<script.*?</script>", re.S), "",
html_text)
print(html_text)
tree = html.fromstring(html_text)
texts = tree.xpath('.//text()')
text = ""
for a in texts:
text = text + str(a).replace("\\n", ".").strip()
#!/usr/bin/env python
# coding=utf-8
from common.inc_csv import Csv_base
from common.inc_file import File_file
from lxml import html
import re
csv = Csv_base()
file = File_file()
def replaceStr(a):
print(a)
a = re.sub(re.compile(r"收藏查看我的收藏(\d+)有用(.*?)(\d+)已投票(\d+)", re.S), "", a)
a = str(a).replace("编辑锁定", " ").strip()
a = str(a).replace("讨论999", " ").strip()
a = str(a).replace("本词条缺少概述图，补充相关内容使词条更完整，还能快速升级，赶紧来编辑吧！", " ").strip()
a = str(a).replace(
"百度百科内容由网友共同编辑，如您发现自己的词条内容不准确或不完善，欢迎使用本人词条编辑服务（免费）参与修正。", " ").strip()
a = str(a).replace("立即前往 >>", " ").strip()
print(a)
return a
if __name__ == '__main__':
csv_data_path = "../../data/百科候选关键词.csv"
rows = csv.read_csv_file(csv_data_path)
for row in rows:
try:
