in my code i have to functions inside scrapy class. start_request takes data from excel workbook and assigns value to plate_num_xlsx
variable.
def start_requests(self):
df=pd.read_excel('data.xlsx')
columnA_values=df['PLATE']
for row in columnA_values:
global plate_num_xlsx
plate_num_xlsx=row
print("+",plate_num_xlsx)
base_url =f"https://dvlaregistrations.dvla.gov.uk/search/results.html?search={plate_num_xlsx}&action=index&pricefrom=0&priceto=&prefixmatches=¤tmatches=&limitprefix=&limitcurrent=&limitauction=&searched=true&openoption=&language=en&prefix2=Search&super=&super_pricefrom=&super_priceto="
url=base_url
yield scrapy.Request(url,callback=self.parse)
But, on each iteration it should invoke parse() method of Scrapy class and inside that function with each iterated newly value of plate_num_xlsx
needs to compare the parsed value, As I understood after print statements it first takes all values, assigns them then only with last value assigned calls parse() method. But for my crawler to function properly I need each time assigning happens to call and use that value inside def parse(). code is below;
import scrapy
from scrapy.crawler import CrawlerProcess
import pandas as pd
itemList=[]
class plateScraper(scrapy.Spider):
name = 'scrapePlate'
allowed_domains = ['dvlaregistrations.dvla.gov.uk']
def start_requests(self):
df=pd.read_excel('data.xlsx')
columnA_values=df['PLATE']
for row in columnA_values:
global plate_num_xlsx
plate_num_xlsx=row
print("+",plate_num_xlsx)
base_url =f"https://dvlaregistrations.dvla.gov.uk/search/results.html?search={plate_num_xlsx}&action=index&pricefrom=0&priceto=&prefixmatches=¤tmatches=&limitprefix=&limitcurrent=&limitauction=&searched=true&openoption=&language=en&prefix2=Search&super=&super_pricefrom=&super_priceto="
url=base_url
yield scrapy.Request(url,callback=self.parse)
def parse(self, response):
for row in response.css('div.resultsstrip'):
plate = row.css('a::text').get()
price = row.css('p::text').get()
a = plate.replace(" ", "").strip()
print(plate_num_xlsx,a,a == plate_num_xlsx)
if plate_num_xlsx==plate.replace(" ","").strip():
item= {"plate": plate.strip(), "price": price.strip()}
itemList.append(item)
yield item
else:
item = {"plate": plate_num_xlsx, "price": "-"}
itemList.append(item)
yield item
with pd.ExcelWriter('output_res.xlsx', mode='r+',if_sheet_exists='overlay') as writer:
df_output = pd.DataFrame(itemList)
df_output.to_excel(writer, sheet_name='result', index=False, header=True)
process = CrawlerProcess()
process.crawl(plateScraper)
process.start()
Using global variables with scrapy in this manner will not work due to it's asynchronous runtime behavior. What you can do alternatively is pass the plate_num_xlsx
variable as a callback keyword argument to the request object itself.
for example:
plate_num_xlsx=row
base_url =f"https://dvlaregistrations.dvla.gov.uk/search/results.html?search={plate_num_xlsx}&action=index&pricefrom=0&priceto=&prefixmatches=¤tmatches=&limitprefix=&limitcurrent=&limitauction=&searched=true&openoption=&language=en&prefix2=Search&super=&super_pricefrom=&super_priceto="
url=base_url
yield scrapy.Request(url,callback=self.parse, cb_kwargs={'plate_num_xlsx': plate_num_xlsx})
def parse(self, response, plate_num_xlsx=None):
for row in response.css('div.resultsstrip'):
plate = row.css('a::text').get()
price = row.css('p::text').get()
...
Now the variable will be included as a parameter to the parse function.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.