将来自beautifulsoup的抓取数据放入CSV文件

问题描述

我想将我从网站上抓取的数据放入一个csv文件中，我的第一次尝试是使用scrapy，但是我无法正确获取语法。当我设法使用beautifulsoup进行操作时，我只是不知道如何将其放入csv文件中。

import requests
from bs4 import BeautifulSoup


URL = "https://www.practo.com/tests/glycosylated-haemoglobin-blood/p?city=delhi"
page = requests.get(URL)
#print(page)
soup=BeautifulSoup(page.content,'html.parser')
results = soup.find(id='root-app')
#print(results.prettify())
job_elems = results.find_all('div',class_='u-padrl--std')
#<h1 class="o-font-size--24 u-font-bold u-marginb--std">HbA1c Test</h1

for job_elem in job_elems:
    title_elem = job_elem.find('h1',class_='o-font-size--24 u-font-bold u-marginb--std')
    also_kNown = job_elem.find('span',class_="u-font-bold")
    cost = job_elem.find('div',class_="o-font-size--22 u-font-bold o-f-color--primary")
    what_test = job_elem.find('div',class_="c-markdown--unstyled")

    #test_prep = job_elem.find('div',class_="c-tabsection__content c-pp__accordion-item__content active")
    #temp = job_elem.find('p')
    print(title_elem.text)
    print(also_kNown.text)
    print(cost.text)
    print(what_test.text)
    #print(temp.text)
    #print(test_prep.text)
    print()

text_content = results.find_all('div',class_='c-markdown--unstyled')
# c-tabsection__content c-pp__accordion-item__content active
# c-tabsection c-pp__accordion-item u-br-rule u-padtb--std--half active
for item in text_content:
    prep = item.find('p')
    #,class_="c-tabsection__content c-pp__accordion-item__content active")
    print(prep.text)
    print('xxo')

解决方法

您可以使用xlsxwriter库。

import xlsxwriter

workbook = xlsxwriter.Workbook("file.xlsx")
worksheet = workbook.add_worksheet()

worksheet.write(row,column,element)

workbook.close()

,

import requests
from bs4 import BeautifulSoup
# import the csv module 
import csv

URL = "https://www.practo.com/tests/glycosylated-haemoglobin-blood/p?city=delhi"
page = requests.get(URL)
#print(page)
soup=BeautifulSoup(page.content,'html.parser')
results = soup.find(id='root-app')
#print(results.prettify())
job_elems = results.find_all('div',class_='u-padrl--std')
#<h1 class="o-font-size--24 u-font-bold u-marginb--std">HbA1c Test</h1
rows = []
fields = ['title_elem','also_known','cost','what_test']
filename = "myfile.csv"
for job_elem in job_elems:
    title_elem = job_elem.find('h1',class_='o-font-size--24 u-font-bold u-marginb--std').text.encode("utf-8")
    also_known = job_elem.find('span',class_="u-font-bold").text.encode("utf-8")
    cost = job_elem.find('div',class_="o-font-size--22 u-font-bold o-f-color--primary").text.encode("utf-8")
    what_test = job_elem.find('div',class_="c-markdown--unstyled").text.encode("utf-8")
    row = [title_elem,also_known,cost,what_test]
    rows.append(row)

with open(filename,'w') as csvfile: 
    # creating a csv writer object 
    csvwriter = csv.writer(csvfile)   
    # writing the fields 
    csvwriter.writerow(fields)   
    # writing the data rows 
    csvwriter.writerows(rows)

text_content = results.find_all('div',class_='c-markdown--unstyled')
# c-tabsection__content c-pp__accordion-item__content active
# c-tabsection c-pp__accordion-item u-br-rule u-padtb--std--half active
for item in text_content:
    prep = item.find('p')
    #,class_="c-tabsection__content c-pp__accordion-item__content active")
    print(prep.text)
    print('xxo')