问网络爬虫美汤

EN

from bs4 import BeautifulSoup

html_doc = """
  <tr class="calendar__row calendar_row calendar__row--grey calendar__row--no-grid nogrid" data-eventid="117390" data-ecobaseid="159" data-touchable="">

    <td class="calendar__cell calendar__impact impact calendar__impact calendar__impact--high">
        <div class="calendar__impact-icon calendar__impact-icon--screen">
            <span title="High Impact Expected" class="high"></span>
        </div>
        <div class="calendar__impact-icon calendar__impact-icon--print">
            <img src="https://resources.faireconomy.media/images/sprites/mm-impact-red.png" alt="" width="14" height="12">
        </div>
    </td>

    <td class="calendar__cell calendar__currency currency calendar__currency--right-of-impact" title="United States">
            US
    </td>   

    <td class="calendar__cell calendar__event event">
        <div>
            <span class="calendar__event-title">Average Hourly Earnings m/m</span>
        </div>
    </td>

  </tr>
"""

soup = BeautifulSoup(html_doc, "html.parser")

for calendar_row in soup.select("tr.calendar_row"):
    if not calendar_row.find(class_="high"):
        continue

    event = calendar_row.find(class_="event")
    print(event.get_text(strip=True))

Average Hourly Earnings m/m

event = soup.select_one(".calendar_row:has(.high) .event")
print(event.get_text(strip=True))