import requests
from lxml import etree
from io import StringIO, BytesIO
def getPage(url):
return requests.get(url)
def main():
parser = etree.HTMLParser(encoding="utf-8")
resp_obj = getPage("https://freelance.ru/projects/?spec=4&page=1")
page = resp_obj.content.decode(resp_obj.encoding).encode('utf-8').decode("utf-8")
tree = etree.parse(StringIO(page), parser)
root = tree.getroot()
div_projects = root.xpath("//div[@class='projects']")[0]
projects = div_projects.xpath('.//div[contains(@class, "public")]')
for project in projects:
print(etree.tostring(project,encoding='UTF-8',pretty_print=True, method="html"))
main()
input()
Π Π½Π° Π²ΡΠ²ΠΎΠ΄Π΅ ΠΏΠΎΠ»ΡΡΠ°Ρ
«\xd0 \xb0» ΠΈ Ρ.Π΄. Π²ΠΌΠ΅ΡΡΠΎ ΠΊΠΈΡΠΈΠ»Π»ΠΈΡΡ
ΠΠΎΠΆΠ΅Ρ ΠΊΡΠΎ ΠΏΠΎΠ΄ΡΠΊΠ°ΠΆΠ΅Ρ, ΠΊΠ°ΠΊ Π½ΠΎΡΠΌΠ°Π»ΡΠ½ΠΎ Π²ΡΠ²Π΅ΡΡΠΈ?
1 ΠΡΠ²Π΅ΡΡ
ΠΡΠΈΠΌΠ΅Ρ, ΠΊΠΎΠ΄ΠΈΡΠΎΠ²ΠΊΠ° ΠΈ ΡΠ°ΠΉΡΠ° ΠΈ Π²ΡΠ²ΠΎΠ΄Π° ΡΡΠΈΡΠ°Π΅ΠΌ utf-8
r = requests.get(url.strip())
html = lxml.html.fromstring(r.text)
title = html.xpath('//title/text()')[0].strip()
content = etree.tounicode(html.get_element_by_id('page_content'))
Π Π΅ΠΊΠΎΠΌΠ΅Π½Π΄ΡΠ΅ΡΡΡ ΠΈΡΠΏΠΎΠ»ΡΠ·ΠΎΠ²Π°ΡΡ tostring, Π½ΠΎ ΡΡΠΎ Π·Π°Π²ΠΈΡΠΈΡ ΠΎΡ Π²Π΅ΡΡΠΈΠΈ lxml Π½Π° ΠΊΠΎΠΌΠΏΡΡΡΠ΅ΡΠ΅
Deprecated: use tostring(el, encoding='unicode') instead.
Π’ΠΎΠ»ΡΠΊΠΎ ΡΠ΅ΡΠ΅Π· xpath
import requests
import lxml.html
url = 'https://freelance.ru/projects/?spec=4&page=1'
r = requests.get(url)
html = lxml.html.fromstring(r.text)
title = html.xpath('//title/text()')[0].strip()
first_topic = html.xpath(".//*[@id='col_center']/div/div[2]/div[1]/div/h2/a/span/text()")
ΠΠ°ΠΏΠΈΡΠΈΡΠ΅ ΡΠ²ΠΎΠΉ ΠΎΡΠ²Π΅Ρ Π½Π° Π΄Π°Π½Π½ΡΠΉ Π²ΠΎΠΏΡΠΎΡ.