一个简单的demo,python爬虫,其实是以前的存货,很久很久没有写爬虫了,渣渣更渣了啊!
爬取财富中文网,2020年《财富》中国500强排行榜相关数据,数据都在网页源码里,结构也比较清晰,基本上一个请求页面可以搞定所有数据,一个老哥要的数据,用来做数据分析!
新人可以用来练手的网站,这里给出参考demo,仅供参考和学习使用!
fake_useragent库本地使用
来自于吾爱破解网站(ID:jxt441621944)上的分享,fake_useragent库也是本渣渣比较喜欢使用的一个库,比较方便吧,好用倒也说不上,看着用吧,fake_useragent库本地使用方法,这里给大家整理和打包了一下!
UserAgent就是用户代{过}{滤}理,是一串字符串,相当于是浏览器的身份证明,在写爬虫的时候频繁更换请求头中的UserAgent可以避免触发反爬机制(配合代{过}{滤}理IP食用更佳)。
fake_useragent就是可以获得一个随机的用户代{过}{滤}理的库。
打包地址获取 关注微信公众号:二爷记 后台回复 “UA”
fake_useragent库总共250条UA!
UA库文件:fake_ua.txt
py调用文件:fakeua.py
#ua库使用
#微信:huguo00289
# -*- coding: UTF-8 -*-
import random
with open('fake_ua.txt', 'r') as f:
fake_ua = [fua.strip() for fua in f.readlines()]
print(random.choice(fake_ua))
python爬虫2020年《财富》中国500强排行榜数据爬取demo
没啥好说的,照着抄吧,本渣渣也是抄的的,不懂的尽量百度
也可以加本渣渣微信:huguo00289
交流探讨学习!
#财富爬取
#微信:huguo00289
# -*- coding: UTF-8 -*-
import requests,random
from lxml import etree
import xlsxwriter
class Httprequest(object):
ua_list = [
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36Chrome 17.0',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0Firefox 4.0.1',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
]
@property #把方法变成属性的装饰器
def random_headers(self):
return {
'User-Agent': random.choice(self.ua_list)
}
class Get_data(Httprequest):
def __init__(self):
self.url="http://www.fortunechina.com/fortune500/c/2020-07/27/content_369925.htm"
self.murl="http://www.fortunechina.com/fortune500/c/2020-05/18/content_365275.htm"
def get_data(self):
html=requests.get(self.url,headers=self.random_headers,timeout=5).content.decode('utf-8')
#print(html)
req = etree.HTML(html)
rankings=req.xpath('//table[@class="wt-table"]/tbody/tr/td[1]/text()')
last_rankings=req.xpath('//table[@class="wt-table"]/tbody/tr/td[2]/text()')
companys=req.xpath('//table[@class="wt-table"]/tbody/tr/td[3]/a/text()')
incomes=req.xpath('//table[@class="wt-table"]/tbody/tr/td[4]/text()')
profits=req.xpath('//table[@class="wt-table"]/tbody/tr/td[5]/text()')
# print(ranking)
# print(last_ranking)
# print(company)
# print(income)
# print(profit)
data_list=[]
for ranking,last_ranking,company,income,profit in zip(
rankings, last_rankings, companys, incomes, profits
):
data = [
ranking,last_ranking,company,income,profit
]
print(data)
data_list.append(data)
print('\n')
self.write_to_xlsx(data_list)
def write_to_xlsx(self, data_list):
workbook = xlsxwriter.Workbook('{}_search_results.xlsx'.format("2020年《财富》中国500强排行榜")) # 创建一个Excel文件
worksheet = workbook.add_worksheet("2020年《财富》中国500强排行榜")
title = ['排名', '上年排名', '公司名称(中文)', '营业收入(百万元)', '利润(百万元)'] # 表格title
worksheet.write_row('A1', title)
for index, data in enumerate(data_list):
# content = content.rstrip()
# keyword, rank, include_num, chart_url, title, game_id, company_num, long_words_num = data
num0 = str(index + 2)
row = 'A' + num0
# data = [name, size, game_id]
worksheet.write_row(row, data)
workbook.close()
def get_mdata(self):
html=requests.get(self.murl,headers=self.random_headers,timeout=5).content.decode('utf-8')
#print(html)
req = etree.HTML(html)
rankings=req.xpath('//table[@class="wt-table"]/tbody/tr/td[1]/text()')
companys=req.xpath('//table[@class="wt-table"]/tbody/tr/td[2]/a/text()')
incomes=req.xpath('//table[@class="wt-table"]/tbody/tr/td[3]/text()')
profits=req.xpath('//table[@class="wt-table"]/tbody/tr/td[4]/text()')
data_list=[]
for ranking,company,income,profit in zip(
rankings,companys, incomes, profits
):
data = [
ranking,company,income,profit
]
print(data)
data_list.append(data)
print('\n')
self.write_to_mxlsx(data_list)
def write_to_mxlsx(self, data_list):
workbook = xlsxwriter.Workbook('{}_search_results.xlsx'.format("2020年《财富》美国500强排行榜")) # 创建一个Excel文件
worksheet = workbook.add_worksheet("2020年《财富》美国500强排行榜")
title = ['排名', '公司名称(中文)', '营业收入(百万美元)', '利润(百万美元)'] # 表格title
worksheet.write_row('A1', title)
for index, data in enumerate(data_list):
# content = content.rstrip()
# keyword, rank, include_num, chart_url, title, game_id, company_num, long_words_num = data
num0 = str(index + 2)
row = 'A' + num0
# data = [name, size, game_id]
worksheet.write_row(row, data)
workbook.close()
if __name__=="__main__":
spider=Get_data()
#spider.get_data()
spider.get_mdata()
微信公众号:二爷记
不定时分享python源码及工具