Python网络爬虫

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='gb')  # 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=&searchword={query}&keyword={query}&token=12..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: #;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='gb')  # 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=&perpage=&templet=&token=12..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=&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='gb')  # 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=&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=&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='gb')  # 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=&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='gb')  # 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=&searchword={query}&keyword={query}&token=12..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='gb')  # 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=&searchword={query}&keyword={query}&token=12..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='gb')  # 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=&searchword={query}&keyword={query}&token=12..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: #;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('----------------------------')

目前成都创新互联公司已为1000多家的企业提供了网站建设、域名、虚拟空间、网站托管、企业网站设计、松北网站维护等服务，公司将坚持客户导向、应用为本的策略，正道将秉承"和谐、参与、激情"的文化，与客户和合作伙伴齐心协力一起成长，共同发展。

转载请注明出处，谢谢！！！