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://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 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://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://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://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)
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)
# -- coding: UTF-8 --
from common.HtmlSource import HtmlSource
from common.Rule import Rule
#from common.inc_conn import Conn_mysql
from common.inc_csv import Csv_base
from common.inc_file import File_file, File_floder
import requests
from lxml import html
import time
floder = File_floder()
htmlSource = HtmlSource()
rule = Rule()
csv = Csv_base()
flag = 0
commontitle = 1
# 多线程
def read_detial(url, path):
if (str(url[0][1]).startswith("http") and url[1][1] != "收起"):
# TODO 翻页
for i in range(1, 11):
print(url[0][1])
detial_html = htmlSource.get_html(url_p=url[0][1] +
"/?page=%d" % i,
type_p='rg')
tree = html.fromstring(detial_html)
hreflist = tree.xpath(
'//ul[@class="list"]/li/div/div/p[@class="name"]/a/@href')