Python Forum

Hi. I'm just started with Python and trying to practicing.

I parse a website and creating a list with dictionaries and it works well, then I trying to export it and getting errors


Full code

import requests
from bs4 import BeautifulSoup as bs
import xlwt


headers =  {'accept': '*/*',
             'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.2 Safari/605.1.15'
}

base_url = 'https://hh.ru/search/vacancy?search_period=3&area=1&text=python&page=0'

def hh_parse(base_url, headers):
    jobs = []
    session = requests.Session()
    request = session.get(base_url, headers=headers)
    if request.status_code == 200:
        soup = bs(request.content, 'html.parser')
        divs = soup.find_all('div', attrs={'data-qa': 'vacancy-serp__vacancy'})
        for div in divs:
            title = div.find('a', attrs ={'data-qa': 'vacancy-serp__vacancy-title'}).text
            href = div.find('a', attrs={'data-qa': 'vacancy-serp__vacancy-title'})['href']
            company = div.find('a', attrs={'data-qa': 'vacancy-serp__vacancy-employer'}).text
            text1 = div.find('div', attrs ={'data-qa': 'vacancy-serp__vacancy_snippet_responsibility'}).text
            text2 = div.find('div', attrs={'data-qa': 'vacancy-serp__vacancy_snippet_requirement'}).text
            content = text1 + ' ' + text2
            jobs.append({
                'title': title,
                'href': href,
                'company': company,
                'content': content
            })
        print(len(jobs))


        wb = xlwt.Workbook()
        ws = wb.add_sheet("Export")

        for i in jobs:
            next_string = 0 + 1
            ws.write(next_string, 1, i['title'])
            ws.write(next_string, 2, i['href'])
            ws.write(next_string, 3, i['company'])
            ws.write(next_string, 4, i['content'])
          

        wb.save("Export.xls")
    else:
        print('ERROR')

hh_parse(base_url, headers)

Answer

Output:
/Users/ak/Documents/Python/Practice/RusrekParse/mlsvenv/bin/python /Users/ak/Documents/Python/Practice/RusrekParse/rusrek_murr.py
16
Traceback (most recent call last):
  File "/Users/ak/Documents/Python/Practice/RusrekParse/rusrek_murr.py", line 53, in <module>
    hh_parse(base_url, headers)
  File "/Users/ak/Documents/Python/Practice/RusrekParse/rusrek_murr.py", line 40, in hh_parse
    ws.write(next_string, 1, i['title'])
  File "/Users/ak/Documents/Python/Practice/RusrekParse/mlsvenv/lib/python3.7/site-packages/xlwt/Worksheet.py", line 1088, in write
    self.row(r).write(c, label, style)
  File "/Users/ak/Documents/Python/Practice/RusrekParse/mlsvenv/lib/python3.7/site-packages/xlwt/Row.py", line 235, in write
    StrCell(self.__idx, col, style_index, self.__parent_wb.add_str(label))
  File "/Users/ak/Documents/Python/Practice/RusrekParse/mlsvenv/lib/python3.7/site-packages/xlwt/Row.py", line 154, in insert_cell
    raise Exception(msg)
Exception: Attempt to overwrite cell: sheetname='Export' rowx=1 colx=1

Process finished with exit code 1

---

Fixed myself