Question

import urllib2    
from selenium import webdriver    
from selenium.webdriver.common.by import By    
from selenium.webdriver.common.keys import Keys

url = ("http://www.justdial.com/Mumbai/CA")    
driver = webdriver.Firefox()    
driver.get(url)

driver

elements = driver.find_elements_by_xpath('//div[@class="col-md-12 col-xs-12 padding0"]')

for e in elements:    
    print e.text    
url = driver.current_url    
company_name = driver.find_element_by_xpath('//span[@class="jcn"]').text

contact_number = driver.find_element_by_xpath('//p[@class="contact_info"]').text    
address = driver.find_element_by_xpath('//p[@class="adress_info"]').text    
address_info = driver.find_element_by_xpath('//p[@class="address-info adinfoex"]').text

estd = driver.find_element_by_xpath('//li[@class="fr"]').text    
ratings = driver.find_element_by_xpath('//li[@class="last"]').text

tf = 'textfile.csv'    
f2 = open(tf, 'a+')

f2.write(', '.join([data.encode('utf-8') for data in [company_name]]) + ',')    
f2.write(', '.join([data.encode('utf-8') for data in [contact_number]]) + ',')    
f2.write(', '.join([data.encode('utf-8') for data in [address]]) + ',')    
f2.write(', '.join([data.encode('utf-8') for data in [address_info]]) + ',')    
f2.write(', '.join([data.encode('utf-8') for data in [estd_ratings]]) + '\n')

f2.close()

Answer 1

以下内容应该让您入门。重要的是确保您的xpath条目准确选择您需要的内容。 Python的csv module可用于将自动获得的列表转换为逗号分隔的条目，而无需添加自己的逗号：

SELECT 
  postcode, 
  ( 3959 * acos( cos( radians( 53.1852582 ) ) * cos( radians( latitude ) ) * cos( radians( longitude ) - radians(-3.0198408999999997) ) + sin( radians(53.1852582) ) * sin( radians( latitude ) ) ) ) AS distance
FROM 
  uk_postcodes
WHERE 
  longitude BETWEEN <longitude1> AND <longitude2> 
AND 
  latitude BETWEEN <latitude1> AND <latitude2>
ORDER BY 
  distance ASC
LIMIT 1;

这将为您提供类似以下内容的CSV文件：

import csv
import urllib2    
from selenium import webdriver    
from selenium.webdriver.common.by import By    
from selenium.webdriver.common.keys import Keys

def get_elements_by_xpath(driver, xpath):
    return [entry.text for entry in driver.find_elements_by_xpath(xpath)]


url = ("http://www.justdial.com/Mumbai/CA")    
driver = webdriver.Firefox()    
driver.get(url)

search_entries = [
    ("CompanyName",     "//span[@class='jcn']"),
    ("ContactNumber",   "//p[@class='contact-info']/span/a"),
    ("Address",         "//span[@class='desk-add jaddt']"),
    ("AddressInfo",     "//p[@class='address-info adinfoex']"),
    ("Estd",            "//li[@class='fr']"),
    ("Ratings",         "//li[@class='last']/a/span[@class='rt_count']")]

with open('textfile.csv', 'wb') as f_output:
    csv_output = csv.writer(f_output)

    # Write header
    csv_output.writerow([name for name, xpath in search_entries])
    entries = []

    for name, xpath in search_entries:
        entries.append(get_elements_by_xpath(driver, xpath))

    csv_output.writerows(zip(*entries))

循环请求每个xpath搜索并为每次搜索创建一个数组条目。每次搜索都会返回一个匹配数组，因此最终会得到一个条目数组。

然后需要将其写入CSV文件。 CompanyName,ContactNumber,Address,AddressInfo,Estd,Ratings Bansal Investment & Consult...,+(91)-22-38578062,Manpada-thane West.. | more..,"CA, Tax Consultants, more...",Estd.in 2003,27 Ratings G.Kedia & Associates,+(91)-22-38555914,"Station Road, Thane We.. | more..","CA, Company Registration Consultants, more...",Estd.in 2010,17 Ratings Tarun Shah & Associates,+(91)-22-38552775,"Mogra Lane, Andheri Ea.. | more..","CA, Income Tax Consultants, more...",Estd.in 2000,12 Ratings Hemant Shah And Associates LLP,+(91)-22-38588696,"Azad Road, Andheri Eas.. | more..","CA, Company Secretary, more...",Estd.in 1988,65 Ratings按列顺序排列，CSV文件需要按行顺序写入。为此，entries用于转换为行顺序。由于整个数组现在的顺序正确，因此可以使用zip(*entries)的单个调用一次性写入整个文件。

使用Python的CSV库的另一个好处是，如果任何字段包含逗号，它将自动在字段周围添加引号以确保Excel不读取将其解释为另一列。请注意，您可能需要在加载时更改默认的单元格类型格式，因为Excel会尝试猜测。

如何以Excel格式输出Python Selenium代码？

1 个答案: