Python网络爬虫 - 爬取中证网银行相关信息
最终版:07_中证网(Plus -Pro).py
# coding=utf-8
import requests
from bs4 import BeautifulSoup
import io
import sys
import os
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改变标准输出的默认编码
for qq in range(8):
# query = input("【中证网】请输入你想搜索的内容:")
query = '苏州银行'
#年份
year = [2014,2015,2016,2017,2018,2019,2020,2021]
#总页数
pages = [2,1,1,1,11,1,19,7]
year = year[qq]
pages = pages[qq]
if not os.path.isdir(f'D:/桌面/爬虫-银行/中国证券网/{query}'): # 如果没有此文件夹
os.mkdir(f'D:/桌面/爬虫-银行/中国证券网/{query}') # 创建此文件夹
m = 0
for p in range(1, pages + 1):
url = f'http://search.cs.com.cn/search?page={p}&channelid=215308&searchword={query}&keyword={query}&token=12.1462412070719.47&perpage=10&outlinepage=5&&andsen=&total=&orsen=&exclude=&searchscope=×cope=×copecolumn=&orderby=&timeline=={year}'
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find_all("table")
datalist = []
for ii in alist:
ss=ii.find('td', style='font-size: 12px;line-height: 24px;color: #333333;margin-top: 4px;')
# print('ss=\n\n',ss)
if ss != None:
ss = ss.get_text()
datalist.append(ss)
# print('data:',datalist,len(datalist))
if not os.path.isdir(f'D:/桌面/爬虫-银行/中国证券网/{query}/{year}'): # 如果没有此文件夹
os.mkdir(f'D:/桌面/爬虫-银行/中国证券网/{query}/{year}') # 创建此文件夹
for ii in range(len(datalist)):
fp = open(f'D:/桌面/爬虫-银行/中国证券网/{query}/{year}/({year}){ii + m + 1}.txt', 'w+', encoding='utf-8')
fp.write(datalist[ii] + '\n') # 只包含文本
print(datalist[ii])
print(f'\n> > >{year}年,第{p}页,第{ii + 1}篇,成功! < < <')
fp.close()
m = m + len(datalist) + 1
print('----------------------------')
print(f'------\n{year}年,爬取完毕----')
print('----------------------------')
历史优化记录:01_中证网.py
# coding=utf-8
import requests
from bs4 import BeautifulSoup
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改变标准输出的默认编码
query = input("【中证网】请输入你想搜索的内容:")
pages = int(input("要爬取的页数(不小于1):"))
if pages < 1:
exit()
url = f'http://search.cs.com.cn/search?channelid=215308&perpage=&templet=&token=12.1462412070719.47&searchword={query}'
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 "
"Safari/537.36 SLBrowser/7.0.0.6241 SLBChan/30"}
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find("table").find_all("a")
# print(alist)
weblist = []
for a in alist:
if a.get('href')[:5] == "https":
weblist.append(a.get('href'))
# ----------------单页每个文章---------------------------------
m = 0
for ii in range(len(weblist)):
url_a = weblist[ii]
# print('0=',url_a)
dic_a = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 "
"Safari/537.36 SLBrowser/7.0.0.6241 SLBChan/30"}
resp_a = requests.get(url_a, headers=dic_a, )
resp_a.encoding = 'gbk'
# print('New:\n',resp_a.text)
page_a = BeautifulSoup(resp_a.text, "html.parser") # 指定html解析器
# print('123:\n',page_a)
page_b = page_a.find('section').find_all('p')
# print(page_b)
fp=open(f'D:/桌面/爬虫-银行/中国证券网/中国银行/{ii+1}.txt','w+',encoding='utf-8')
txt_list = []
for txt_a in page_b:
# print(txt_a.text)
txt_list.append(txt_a.text)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# ++++++++++++++++++++++文本写入+++++++++++++++++++++++++++++++
for i in range(len(txt_list)):
fp.write(txt_list[i] + '\n') # 只包含文本
fp.close()
print(f'>>{ii+1}成功!')
m = ii+1
# +-+++-----------++++++++++-----多页------++++++++++++----------++++
if pages > 1:
for p in range(pages):
url_s = f"http://search.cs.com.cn/search?page={p+1}&channelid=215308&searchword={query}"
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find("table").find_all("a")
# print(alist)
weblist = []
for a in alist:
if a.get('href')[:5] == "https":
weblist.append(a.get('href'))
# ----------------单页每个文章---------------------------------
for ii in range(len(weblist)):
url_a = weblist[ii]
# print('0=',url_a)
dic_a = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 "
"Safari/537.36 SLBrowser/7.0.0.6241 SLBChan/30"}
resp_a = requests.get(url_a, headers=dic_a, )
resp_a.encoding = 'gbk'
# print('New:\n',resp_a.text)
page_a = BeautifulSoup(resp_a.text, "html.parser") # 指定html解析器
# print('123:\n',page_a)
page_b = page_a.find('section').find_all('p')
# print(page_b)
fp = open(f'D:/桌面/爬虫-银行/中国证券网/中国银行/{ii + 1 + m}.txt', 'w+', encoding='utf-8')
txt_list = []
for txt_a in page_b:
# print(txt_a.text)
txt_list.append(txt_a.text)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# ++++++++++++++++++++++文本写入+++++++++++++++++++++++++++++++
for i in range(len(txt_list)):
fp.write(txt_list[i] + '\n') # 只包含文本
print(f'>>{ii + 1 + m}成功!')
m = m + ii + 1
fp.close()
print('---------------\n>>>爬取完毕<<<')
历史优化记录:02_中证网.py
# coding=utf-8
import requests
from bs4 import BeautifulSoup
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改变标准输出的默认编码
query = input("【中证网】请输入你想搜索的内容:")
pages = int(input("要爬取的页数(不小于1):"))
if pages < 1:
exit()
url = f'http://search.cs.com.cn/search?page=1&channelid=215308&searchword={query}'
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 "
"Safari/537.36 SLBrowser/7.0.0.6241 SLBChan/30"}
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find("table").find_all("a")
# print(alist)
weblist = []
for a in alist:
if a.get('href')[:5] == "https":
weblist.append(a.get('href'))
# ----------------单页每个文章---------------------------------
m = 0
for ii in range(len(weblist)):
url_a = weblist[ii]
# print('0=',url_a)
dic_a = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 "
"Safari/537.36 SLBrowser/7.0.0.6241 SLBChan/30"}
resp_a = requests.get(url_a, headers=dic_a, )
resp_a.encoding = 'gbk'
# print('New:\n',resp_a.text)
page_a = BeautifulSoup(resp_a.text, "html.parser") # 指定html解析器
# print('123:\n',page_a)
page_b = page_a.find('section').find_all('p')
# print(page_b)
fp=open(f'D:/桌面/爬虫-银行/中国证券网/中国银行/0/(2021){ii+1}.txt','w+',encoding='utf-8')
txt_list = []
for txt_a in page_b:
# print(txt_a.text)
txt_list.append(txt_a.text)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# ++++++++++++++++++++++文本写入+++++++++++++++++++++++++++++++
for i in range(len(txt_list)):
fp.write(txt_list[i] + '\n') # 只包含文本
fp.close()
print(f'>>{ii+1}成功!')
m = ii+1
# +-+++-----------++++++++++-----多页------++++++++++++----------++++
# +-+++-----------++++++++++-----多页------++++++++++++----------++++
if pages > 1:
for p in range(pages):
url_s = f"http://search.cs.com.cn/search?page={p+1}&channelid=215308&searchword={query}"
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find("table").find_all("a")
# print(alist)
weblist = []
for a in alist:
if a.get('href')[:5] == "https":
weblist.append(a.get('href'))
# ----------------单页每个文章---------------------------------
for ii in range(len(weblist)):
url_a = weblist[ii]
# print('0=',url_a)
dic_a = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 "
"Safari/537.36 SLBrowser/7.0.0.6241 SLBChan/30"}
resp_a = requests.get(url_a, headers=dic_a, )
resp_a.encoding = 'gbk'
# print('New:\n',resp_a.text)
page_a = BeautifulSoup(resp_a.text, "html.parser") # 指定html解析器
# print('123:\n',page_a)
page_b = page_a.find('section').find_all('p')
# print(page_b)
fp = open(f'D:/桌面/爬虫-银行/中国证券网/中国银行/0/(2021){ii + 1 + m}.txt', 'w+', encoding='utf-8')
txt_list = []
for txt_a in page_b:
# print(txt_a.text)
txt_list.append(txt_a.text)
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# ++++++++++++++++++++++文本写入+++++++++++++++++++++++++++++++
for i in range(len(txt_list)):
fp.write(txt_list[i] + '\n') # 只包含文本
print(f'>>{ii + 1 + m}成功!')
m = m + ii + 1
fp.close()
print('---------------\n>>>爬取完毕<<<')
历史优化记录:03_中证网.py
# coding=utf-8
import requests
from bs4 import BeautifulSoup
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改变标准输出的默认编码
query = input("【中证网】请输入你想搜索的内容:")
pages = int(input("要爬取的页数(不小于1):"))
if pages < 1:
exit()
m = 0
for p in range(1,pages+1):
url = f'http://search.cs.com.cn/search?page={p}&channelid=215308&searchword={query}&perpage=10&outlinepage=5&&andsen=&total=&orsen=&exclude=&searchscope=×cope=×copecolumn=&orderby=&timeline==2021'
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find("table").find_all('a')
weblist = []
for a in alist:
if a.get('href')[:5] == "https":
weblist.append(a.get('href'))
# print('weblist==',weblist)
# ----------------单页每个文章---------------------------------
for ii in range(len(weblist)):
url_a = weblist[ii]
# print('0=',url_a)
dic_a = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp_a = requests.get(url_a, headers=dic_a, )
resp_a.encoding = 'gbk'
# print('New:\n',resp_a.text)
page_a = BeautifulSoup(resp_a.text, "html.parser") # 指定html解析器
# print('123:\n',page_a)
page_b = page_a.find('section').find_all('p')
# print(page_b)
fp=open(f'D:/桌面/爬虫-银行/中国证券网/中国银行/2021/(2021){ii+m+1}.txt','w+',encoding='utf-8')
txt_list = []
for txt_a in page_b:
# print('txt_a===',txt_a.text)
txt_list.append(txt_a.text)
print(f'\n-++++++++++++++++++第{ii+1}篇文章++++++++++++++++-\n',txt_list,len(txt_list))
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# ++++++++++++++++++++++文本写入+++++++++++++++++++++++++++++++
for i in range(len(txt_list)):
fp.write(txt_list[i] + '\n') # 只包含文本
# print('-----------------------------------')
print(f'\n> > >{ii+1}成功! < < <')
fp.close()
m=m+len(weblist)+1
print('---------------\n>>>爬取完毕<<<')
历史优化记录:04_中证网(网址筛选问题).py
# coding=utf-8
import requests
from bs4 import BeautifulSoup
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改变标准输出的默认编码
query = input("【中证网】请输入你想搜索的内容:")
pages = int(input("要爬取的页数(不小于1):"))
if pages < 1:
exit()
m = 0
for p in range(1,pages+1):
url = f'http://search.cs.com.cn/search?page={pages}&channelid=215308&searchword={query}&keyword={query}&token=12.1462412070719.47&perpage=10&outlinepage=5&&andsen=&total=&orsen=&exclude=&searchscope=×cope=×copecolumn=&orderby=&timeline==2020'
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find("table").find_all('a')
print('alist:',alist)
weblist = []
for a in alist:
if a.get('href')[4:] == "http":
weblist.append(a.get('href'))
print('weblist==',weblist)
# ----------------单页每个文章---------------------------------
for ii in range(len(weblist)):
url_a = weblist[ii]
# print('0=',url_a)
dic_a = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp_a = requests.get(url_a, headers=dic_a, )
resp_a.encoding = 'gbk'
# print('New:\n',resp_a.text)
page_a = BeautifulSoup(resp_a.text, "html.parser") # 指定html解析器
# print('123:\n',page_a)
page_b = page_a.find('section').find_all('p')
# print(page_b)
fp=open(f'D:/桌面/爬虫-银行/中国证券网/中国银行/2020/(2020){ii+m+1}.txt','w+',encoding='utf-8')
txt_list = []
for txt_a in page_b:
# print('txt_a===',txt_a.text)
txt_list.append(txt_a.text)
print(f'\n-++++++++++++++++++第{ii+1}篇文章++++++++++++++++-\n',txt_list,len(txt_list))
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# ++++++++++++++++++++++文本写入+++++++++++++++++++++++++++++++
for i in range(len(txt_list)):
fp.write(txt_list[i] + '\n') # 只包含文本
# print('-----------------------------------')
print(f'\n> > >{ii+1}成功! < < <')
fp.close()
m=m+len(weblist)+1
print('---------------\n>>>爬取完毕<<<')
历史优化记录:05_中证网.py
# coding=utf-8
import requests
from bs4 import BeautifulSoup
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改变标准输出的默认编码
query = input("【中证网】请输入你想搜索的内容:")
year = int(input('要爬取的年份:'))
pages = int(input("要爬取的页数(不小于1):"))
if pages < 1:
exit()
m = 0
for p in range(1, pages + 1):
url = f'http://search.cs.com.cn/search?page={p}&channelid=215308&searchword={query}&keyword={query}&token=12.1462412070719.47&perpage=10&outlinepage=5&&andsen=&total=&orsen=&exclude=&searchscope=×cope=×copecolumn=&orderby=&timeline=={year}'
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find("table").find('tr').find_all('a')
# print('alist:', alist)
weblist = []
for a in alist:
if a.get('href')[:4] == "http":
weblist.append(a.get('href'))
print('weblist==', weblist)
# ----------------单页每个文章---------------------------------
for ii in range(len(weblist)):
url_a = weblist[ii]
# print('0=',url_a)
dic_a = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp_a = requests.get(url_a, headers=dic_a, )
resp_a.encoding = 'gbk'
# print('New:\n',resp_a.text)
page_a = BeautifulSoup(resp_a.text, "html.parser") # 指定html解析器
# print('123:\n',page_a)
page_b = page_a.find_all('p')
# print(page_b)
fp = open(f'D:/桌面/爬虫-银行/中国证券网/中国银行/{year}/({year}){ii + m + 1}.txt', 'w+', encoding='utf-8')
txt_list = []
for txt_a in page_b:
# print('txt_a===',txt_a.text)
txt_list.append(txt_a.text)
print(f'\n-++++++++++++++++++第{ii + 1}篇文章++++++++++++++++-\n', txt_list, len(txt_list))
# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# ++++++++++++++++++++++文本写入+++++++++++++++++++++++++++++++
for i in range(len(txt_list)):
fp.write(txt_list[i] + '\n') # 只包含文本
# print('-----------------------------------')
print(f'\n> > >{ii + 1}成功! < < <')
fp.close()
m = m + len(weblist) + 1
print('---------------\n>>>爬取完毕<<<')
历史优化记录:06_中证网(Plus).py
# coding=utf-8
import requests
from bs4 import BeautifulSoup
import io
import sys
import os
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030') # 改变标准输出的默认编码
# query = input("【中证网】请输入你想搜索的内容:")
query = '交通银行'
year = int(input('要爬取的年份:'))
pages = int(input("要爬取的页数(不小于1):"))
if pages < 1:
exit()
m = 0
for p in range(1, pages + 1):
url = f'http://search.cs.com.cn/search?page={p}&channelid=215308&searchword={query}&keyword={query}&token=12.1462412070719.47&perpage=10&outlinepage=5&&andsen=&total=&orsen=&exclude=&searchscope=×cope=×copecolumn=&orderby=&timeline=={year}'
dic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36"}
resp = requests.get(url, headers=dic, )
resp.encoding = 'utf-8'
# print(resp)
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
print(f'\n>>>--------------------第{p}页---------------------<<<\n')
# print(resp.text)
page = BeautifulSoup(resp.text, "html.parser") # 指定html解析器
alist = page.find_all("table")
datalist = []
for ii in alist:
ss=ii.find('td', style='font-size: 12px;line-height: 24px;color: #333333;margin-top: 4px;')
# print('ss=\n\n',ss)
if ss != None:
ss = ss.get_text()
datalist.append(ss)
# print('data:',datalist,len(datalist))
if not os.path.isdir(f'D:/桌面/爬虫-银行/中国证券网/{query}/{year}'): # 如果没有此文件夹
os.mkdir(f'D:/桌面/爬虫-银行/中国证券网/{query}/{year}') # 创建此文件夹
for ii in range(len(datalist)):
fp = open(f'D:/桌面/爬虫-银行/中国证券网/{query}/{year}/({year}){ii + m + 1}.txt', 'w+', encoding='utf-8')
fp.write(datalist[ii] + '\n') # 只包含文本
print(datalist[ii])
print(f'\n> > >第{p}页,第{ii + 1}篇,成功! < < <')
fp.close()
m = m + len(datalist) + 1
print('----------------------------')
print(f'------\n{year}年,爬取完毕----')
print('----------------------------')
Python网络爬虫 - 爬取中证网银行相关信息的更多相关文章
- 如何利用Python网络爬虫爬取微信朋友圈动态--附代码(下)
前天给大家分享了如何利用Python网络爬虫爬取微信朋友圈数据的上篇(理论篇),今天给大家分享一下代码实现(实战篇),接着上篇往下继续深入. 一.代码实现 1.修改Scrapy项目中的items.py ...
- 利用Python网络爬虫爬取学校官网十条标题
利用Python网络爬虫爬取学校官网十条标题 案例代码: # __author : "J" # date : 2018-03-06 # 导入需要用到的库文件 import urll ...
- 如何用Python网络爬虫爬取网易云音乐歌曲
今天小编带大家一起来利用Python爬取网易云音乐,分分钟将网站上的音乐down到本地. 跟着小编运行过代码的筒子们将网易云歌词抓取下来已经不再话下了,在抓取歌词的时候在函数中传入了歌手ID和歌曲名两 ...
- 04 Python网络爬虫 <<爬取get/post请求的页面数据>>之requests模块
一. urllib库 urllib是Python自带的一个用于爬虫的库,其主要作用就是可以通过代码模拟浏览器发送请求.其常被用到的子模块在Python3中的为urllib.request和urllib ...
- Python网络爬虫-爬取微博热搜
微博热搜的爬取较为简单,我只是用了lxml和requests两个库 url=https://s.weibo.com/top/summary?Refer=top_hot&topnav=1& ...
- python网络爬虫&&爬取网易云音乐
#爬取网易云音乐 url="https://music.163.com/discover/toplist" #歌单连接地址 url2 = 'http://music.163.com ...
- 如何利用Python网络爬虫抓取微信朋友圈的动态(上)
今天小编给大家分享一下如何利用Python网络爬虫抓取微信朋友圈的动态信息,实际上如果单独的去爬取朋友圈的话,难度会非常大,因为微信没有提供向网易云音乐这样的API接口,所以很容易找不到门.不过不要慌 ...
- 如何利用Python网络爬虫抓取微信好友数量以及微信好友的男女比例
前几天给大家分享了利用Python网络爬虫抓取微信朋友圈的动态(上)和利用Python网络爬虫爬取微信朋友圈动态——附代码(下),并且对抓取到的数据进行了Python词云和wordart可视化,感兴趣 ...
- 利用Python网络爬虫抓取微信好友的所在省位和城市分布及其可视化
前几天给大家分享了如何利用Python网络爬虫抓取微信好友数量以及微信好友的男女比例,感兴趣的小伙伴可以点击链接进行查看.今天小编给大家介绍如何利用Python网络爬虫抓取微信好友的省位和城市,并且将 ...
随机推荐
- ElasticSearch安装 --- windows版
文件下载地址: 链接:https://pan.baidu.com/s/1_Cy_Sy1-vOvsUxliM-EZHQ 提取码:qpcv 定义: Elasticsearch 是一个分布式的搜索和分析引擎 ...
- 04 变量 变量作用域 常量final 变量的命名规范
变量 变量是什么:就是可以变化的量! Java是一种强类型语言,每个变量都必须声明其类型. Java变量是程序中最基本的存储单元,其要素包括变量名,变量类型和作用域. 注意事项: 每个变量都有类型,类 ...
- 前端性能优化 —— 使用 BMP 图片代替 canvas.toDataURL
前端开发中有时需要将 canvas 的内容导出成图片文件,例如供 CSS 使用,通常会使用 canvas.toDataURL,兼容性好并且简单. 不过 canvas.toDataURL 显然是非常低效 ...
- mysql 索引模板
DROP TABLE IF EXISTS `table_name`; CREATE TABLE `table_name` ( `id` bigint(20) UNSIGNED NOT NULL AUT ...
- emu8086 调用LED面板的方法
一.实验要求 1.熟悉并掌握 EMU8086 汇编语言调试环境: 2.学习 8086 的指令系统,输入简单的指令,观察各寄存器.内存相关单元以及处理器标志位的变化(所有数据传送类指令,可参考教材用例) ...
- 利用Redis对批量数据实现分布式锁
需求背景 在开发的收入结转平台界面上有一个归集按钮,可以实现抓取结转表里面的多条数据进行归集操作.为了防止多人多电脑同时操作一条数据,我们自己开发了一个简单的基于Redis实现的分布式锁. 代码实现 ...
- JAVA视频笔记(一)
搭建pho开发环境与框架图 韩顺平 第一章: No1 关于文件以及文件夹的管理 将生成的文本文档做成详细信息的形式,显示文件修改时间以及文件大小,便于文件查看和管理,也是对于一名IT人士高效能工作的 ...
- error LNK2019: 无法解析的外部符号 _WinMain@16,该符号在函数。。。使用
一,问题描述 MSVCRTD.lib(crtexew.obj) : error LNK2019: 无法解析的外部符号 _WinMain@16,该符号在函数 ___tmainCRTStartup 中被引 ...
- 面试之Java String 编码相关
实话说,作为一个多年Java老年程序员,直到近来,在没有决心花时间搞清楚Java String的编码相关问题之前, 自己也都还是似懂非懂,一脸懵逼的.设想如果在面试中,有同学能够条理清晰的回答下面的问 ...
- 面试官:说一下Synchronized底层实现,锁升级的具体过程?
面试官:说一下Synchronized底层实现,锁升级的具体过程? 这是我去年7,8月份面试的时候被问的一个面试题,说实话被问到这个问题还是很意外的,感觉这个东西没啥用啊,直到后面被问了一波new O ...